import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

import warnings
warnings.filterwarnings("ignore")

# Removes the limit for the number of displayed columns
pd.set_option("display.max_columns", None)

# Sets the limit for the number of displayed rows
pd.set_option("display.max_rows", 200)

# To build models for prediction
from Scikit-learn.model_selection import train_test_split, cross_val_score, KFold
from Scikit-learn.linear_model import LinearRegression, Ridge, Lasso, ElasticNet
from Scikit-learn.tree import DecisionTreeRegressor
from Scikit-learn.ensemble import RandomForestRegressor,BaggingRegressor

# To encode categorical variables
from Scikit-learn.preprocessing import LabelEncoder

# For tuning the model
from Scikit-learn.model_selection import GridSearchCV

# To check model performance
from Scikit-learn.metrics import make_scorer,mean_squared_error, r2_score, mean_absolute_error

from google.colab import drive
drive.mount('/content/drive')

Mounted at /content/drive

# Read the healthcare dataset file
data = pd.read_csv("filepath/healthcare_data.csv")

# Copying data to another variable to avoid any changes to original data
same_data = data.copy()

# View the first 5 rows of the dataset
data.head()

# View the last 5 rows of the dataset
data.tail()

# Understand the shape of the data
data.shape

(500000, 15)

# Checking the info of the data
data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 500000 entries, 0 to 499999
Data columns (total 15 columns):
 #   Column                             Non-Null Count   Dtype  
---  ------                             --------------   -----  
 0   Available Extra Rooms in Hospital  500000 non-null  int64  
 1   Department                         500000 non-null  object 
 2   Ward_Facility_Code                 500000 non-null  object 
 3   doctor_name                        500000 non-null  object 
 4   staff_available                    500000 non-null  int64  
 5   patientid                          500000 non-null  int64  
 6   Age                                500000 non-null  object 
 7   gender                             500000 non-null  object 
 8   Type of Admission                  500000 non-null  object 
 9   Severity of Illness                500000 non-null  object 
 10  health_conditions                  348112 non-null  object 
 11  Visitors with Patient              500000 non-null  int64  
 12  Insurance                          500000 non-null  object 
 13  Admission_Deposit                  500000 non-null  float64
 14  Stay (in days)                     500000 non-null  int64  
dtypes: float64(1), int64(5), object(9)
memory usage: 57.2+ MB

# To view patientid and the number of times they have been admitted to the hospital
data['patientid'].value_counts()

patientid
126719    21
125695    21
44572     21
126623    21
125625    19
          ..
37634      1
91436      1
118936     1
52366      1
105506     1
Name: count, Length: 126399, dtype: int64

# Dropping patientid from the data as it is an identifier and will not add value to the analysis
data=data.drop(columns=["patientid"])

# Checking for duplicate values in the data
data.duplicated().sum()

0

# Checking the descriptive statistics of the columns
data.describe().T

# List of all important categorical variables
cat_col = ["Department", "Type of Admission", 'Severity of Illness', 'gender', 'Insurance', 'health_conditions', 'doctor_name', "Ward_Facility_Code", "Age"]

# Printing the number of occurrences of each unique value in each categorical column
for column in cat_col:
    print(data[column].value_counts(1))
    print("-" * 50)

Department
gynecology            0.686956
radiotherapy          0.168630
anesthesia            0.088358
TB & Chest disease    0.045780
surgery               0.010276
Name: proportion, dtype: float64
--------------------------------------------------
Type of Admission
Trauma       0.621072
Emergency    0.271568
Urgent       0.107360
Name: proportion, dtype: float64
--------------------------------------------------
Severity of Illness
Moderate    0.560394
Minor       0.263074
Extreme     0.176532
Name: proportion, dtype: float64
--------------------------------------------------
gender
Female    0.74162
Male      0.20696
Other     0.05142
Name: proportion, dtype: float64
--------------------------------------------------
Insurance
Yes    0.78592
No     0.21408
Name: proportion, dtype: float64
--------------------------------------------------
health_conditions
Other                  0.271209
High Blood Pressure    0.228093
Diabetes               0.211553
Asthama                0.188198
Heart disease          0.100947
Name: proportion, dtype: float64
--------------------------------------------------
doctor_name
Dr Sarah     0.199192
Dr Olivia    0.196704
Dr Sophia    0.149506
Dr Nathan    0.141554
Dr Sam       0.111422
Dr John      0.102526
Dr Mark      0.088820
Dr Isaac     0.006718
Dr Simon     0.003558
Name: proportion, dtype: float64
--------------------------------------------------
Ward_Facility_Code
F    0.241076
D    0.238110
B    0.207770
E    0.190748
A    0.093102
C    0.029194
Name: proportion, dtype: float64
--------------------------------------------------
Age
21-30     0.319586
31-40     0.266746
41-50     0.160812
11-20     0.093072
61-70     0.053112
51-60     0.043436
71-80     0.037406
81-90     0.016362
0-10      0.006736
91-100    0.002732
Name: proportion, dtype: float64
--------------------------------------------------

# Function to plot a boxplot and a histogram along the same scale

def histogram_boxplot(data, feature, figsize=(12, 7), kde=False, bins=None):
    """
    Boxplot and histogram combined

    data: dataframe
    feature: dataframe column
    figsize: size of figure (default (12,7))
    kde: whether to the show density curve (default False)
    bins: number of bins for histogram (default None)
    """
    f2, (ax_box2, ax_hist2) = plt.subplots(
        nrows = 2,      # Number of rows of the subplot grid = 2
        sharex = True,  # x-axis will be shared among all subplots
        gridspec_kw = {"height_ratios": (0.25, 0.75)},
        figsize = figsize,
    )                   # Creating the 2 subplots
    sns.boxplot(data = data, x = feature, ax = ax_box2, showmeans = True, color = "violet"
    )                   # Boxplot will be created and a star will indicate the mean value of the column
    sns.histplot(
        data = data, x = feature, kde = kde, ax = ax_hist2, bins = bins, palette = "winter"
    ) if bins else sns.histplot(
        data = data, x = feature, kde = kde, ax = ax_hist2
    )                   # For histogram
    ax_hist2.axvline(
        data[feature].mean(), color = "green", linestyle = "--"
    )                   # Add mean to the histogram
    ax_hist2.axvline(
        data[feature].median(), color = "black", linestyle = "-"
    )                   # Add median to the histogram

histogram_boxplot(data, "Stay (in days)", kde = True, bins = 30)

histogram_boxplot(data, "Admission_Deposit", kde = True, bins = 30)

histogram_boxplot(data, "Visitors with Patient", kde = True, bins = 30)

# Finding the correlation between various columns of the dataset
plt.figure(figsize = (15,7))
sns.heatmap(data.corr(numeric_only = True), annot = True, vmin = -1, vmax = 1, fmt = ".2f", cmap = "Spectral")

<Axes: >

# Function to plot stacked bar plots

def stacked_barplot(data, predictor, target):
    """
    Print the category counts and plot a stacked bar chart

    data: dataframe
    predictor: independent variable
    target: target variable
    """
    count = data[predictor].nunique()
    sorter = data[target].value_counts().index[-1]
    tab1 = pd.crosstab(data[predictor], data[target], margins = True).sort_values(
        by = sorter, ascending = False
    )
    print(tab1)
    print("-" * 120)
    tab = pd.crosstab(data[predictor], data[target], normalize = "index").sort_values(
        by = sorter, ascending = False
    )
    tab.plot(kind = "bar", stacked = True, figsize = (count + 1, 5))
    plt.legend(
        loc = "lower left",
        frameon = False,
    )
    plt.legend(loc = "upper left", bbox_to_anchor = (1, 1))
    plt.show()

sns.barplot(y = 'Ward_Facility_Code', x = 'Stay (in days)', data = data)
plt.show()

stacked_barplot(data, "Ward_Facility_Code", "Department")

Department          TB & Chest disease  anesthesia  gynecology  radiotherapy  \
Ward_Facility_Code                                                             
A                                 4709       15611           0         21093   
All                              22890       44179      343478         84315   
B                                    0           0      103885             0   
C                                 1319        4199           0          9079   
D                                    0           0      119055             0   
E                                16862       24369           0         54143   
F                                    0           0      120538             0   

Department          surgery     All  
Ward_Facility_Code                   
A                      5138   46551  
All                    5138  500000  
B                         0  103885  
C                         0   14597  
D                         0  119055  
E                         0   95374  
F                         0  120538  
------------------------------------------------------------------------------------------------------------------------

stacked_barplot(data, "Ward_Facility_Code", "Severity of Illness")

Severity of Illness  Extreme   Minor  Moderate     All
Ward_Facility_Code                                    
All                    88266  131537    280197  500000
D                      29549   27220     62286  119055
B                      24222   23579     56084  103885
A                      13662    7877     25012   46551
E                      11488   22254     61632   95374
F                       5842   47594     67102  120538
C                       3503    3013      8081   14597
------------------------------------------------------------------------------------------------------------------------

sns.barplot(y = 'Age', x = 'Stay (in days)', data = data)
plt.show()

data.groupby(['doctor_name'])['Department'].agg(Department_Name='unique',Patients_Treated='count')

# Creating dummy variables for the categorical columns
# drop_first=True is used to avoid redundant variables
data = pd.get_dummies(
    data,
    columns = data.select_dtypes(include = ["object", "category"]).columns.tolist(),
    drop_first = True,
)

# Check the data after handling categorical data
data

# Separating independent variables and the target variable
x = data.drop('Stay (in days)',axis=1)

y = data['Stay (in days)']

# Splitting the dataset into train and test datasets
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.2, shuffle = True, random_state = 1)

# Checking the shape of the train and test data
print("Shape of Training set : ", x_train.shape)
print("Shape of test set : ", x_test.shape)

Shape of Training set :  (400000, 41)
Shape of test set :  (100000, 41)

# Function to compute adjusted R-squared
def adj_r2_score(predictors, targets, predictions):
    r2 = r2_score(targets, predictions)
    n = predictors.shape[0]
    k = predictors.shape[1]
    return 1 - ((1 - r2) * (n - 1) / (n - k - 1))


# Function to compute MAPE
def mape_score(targets, predictions):
    return np.mean(np.abs(targets - predictions) / targets) * 100


# Function to compute different metrics to check performance of a regression model
def model_performance_regression(model, predictors, target):
    """
    Function to compute different metrics to check regression model performance

    model: regressor
    predictors: independent variables
    target: dependent variable
    """

    pred = model.predict(predictors)                  # Predict using the independent variables
    r2 = r2_score(target, pred)                       # To compute R-squared
    adjr2 = adj_r2_score(predictors, target, pred)    # To compute adjusted R-squared
    rmse = np.sqrt(mean_squared_error(target, pred))  # To compute RMSE
    mae = mean_absolute_error(target, pred)           # To compute MAE
    mape = mape_score(target, pred)                   # To compute MAPE

    # Creating a dataframe of metrics
    df_perf = pd.DataFrame(
        {
            "RMSE": rmse,
            "MAE": mae,
            "R-squared": r2,
            "Adj. R-squared": adjr2,
            "MAPE": mape,
        },
        index=[0],
    )

    return df_perf

from Scikit-learn.linear_model import LinearRegression

# Initialize the model
model = LinearRegression()

# Fit the model on the training data
model.fit(x_train, y_train)

LinearRegression()

LinearRegression()

# Checking performance on the training data
linear_reg = model_performance_regression(model, x_train, y_train)
linear_reg

# Checking performance on the testing data
linear_reg_test = model_performance_regression(model, x_test, y_test)
linear_reg_test

ridge_model = Ridge() #creating Ridge Regression model
ridge_model.fit(x_train, y_train) # Fitting the data into the model

Ridge()

Ridge()

ridge_reg = model_performance_regression(ridge_model, x_test, y_test) #getting performance metrics on test data
ridge_reg

folds = KFold(n_splits=10, shuffle=True, random_state=1)
params = {'alpha':[0.001, 0.01, 0.1, 0.2, 0.5, 0.9, 1, 5,10,20]}
model = Ridge()
model_cv = GridSearchCV(estimator=model, param_grid=params, scoring='r2', cv=folds, return_train_score=True)
model_cv.fit(x_train,y_train)

GridSearchCV(cv=KFold(n_splits=10, random_state=1, shuffle=True),
             estimator=Ridge(),
             param_grid={'alpha': [0.001, 0.01, 0.1, 0.2, 0.5, 0.9, 1, 5, 10,
                                   20]},
             return_train_score=True, scoring='r2')

GridSearchCV(cv=KFold(n_splits=10, random_state=1, shuffle=True),
             estimator=Ridge(),
             param_grid={'alpha': [0.001, 0.01, 0.1, 0.2, 0.5, 0.9, 1, 5, 10,
                                   20]},
             return_train_score=True, scoring='r2')

Ridge()

Ridge()

model_cv.best_params_ #getting optimised parameters for alpha

{'alpha': 0.1}

ridge_model_tuned = Ridge(alpha=0.1) ##creating Tuned Ridge Regression model using optimised alpha value
ridge_model_tuned.fit(x_train, y_train) # Fitting the data into the tuned model

Ridge(alpha=0.1)

Ridge(alpha=0.1)

ridge_reg_tuned = model_performance_regression(ridge_model_tuned, x_test, y_test) #getting performance metrics on test data
ridge_reg_tuned

lasso_model = Lasso()
lasso_model.fit(x_train, y_train)

Lasso()

Lasso()

lasso_reg = model_performance_regression(lasso_model, x_test, y_test)
lasso_reg

folds = KFold(n_splits=10, shuffle=True, random_state=1)
params = {'alpha':[0.001, 0.01, 0.1, 0.2, 0.5, 0.9, 1, 5,10,20]}
model = Lasso()
model_cv = GridSearchCV(estimator=model, param_grid=params, scoring='r2', cv=folds, return_train_score=True)
model_cv.fit(x_train,y_train)

GridSearchCV(cv=KFold(n_splits=10, random_state=1, shuffle=True),
             estimator=Lasso(),
             param_grid={'alpha': [0.001, 0.01, 0.1, 0.2, 0.5, 0.9, 1, 5, 10,
                                   20]},
             return_train_score=True, scoring='r2')

GridSearchCV(cv=KFold(n_splits=10, random_state=1, shuffle=True),
             estimator=Lasso(),
             param_grid={'alpha': [0.001, 0.01, 0.1, 0.2, 0.5, 0.9, 1, 5, 10,
                                   20]},
             return_train_score=True, scoring='r2')

Lasso()

Lasso()

model_cv.best_params_

{'alpha': 0.001}

lasso_model_tuned = Lasso(alpha=0.001)
lasso_model_tuned.fit(x_train, y_train)

Lasso(alpha=0.001)

Lasso(alpha=0.001)

lasso_reg_tuned = model_performance_regression(lasso_model_tuned, x_test, y_test)
lasso_reg_tuned

elasticnet_model = ElasticNet()
elasticnet_model.fit(x_train, y_train)

ElasticNet()

ElasticNet()

elasticnet_reg = model_performance_regression(elasticnet_model, x_test, y_test)
elasticnet_reg

folds = KFold(n_splits=10, shuffle=True, random_state=1)
params = {'alpha':[0.001, 0.01, 0.1, 0.2, 0.5, 0.9],
         'l1_ratio': [0.001, 0.01, 0.02, 0.03, 0.04, 0.05]}
model = ElasticNet()
model_cv = GridSearchCV(estimator=model, param_grid=params, scoring='r2', cv=folds, return_train_score=True)
model_cv.fit(x_train,y_train)

GridSearchCV(cv=KFold(n_splits=10, random_state=1, shuffle=True),
             estimator=ElasticNet(),
             param_grid={'alpha': [0.001, 0.01, 0.1, 0.2, 0.5, 0.9],
                         'l1_ratio': [0.001, 0.01, 0.02, 0.03, 0.04, 0.05]},
             return_train_score=True, scoring='r2')

GridSearchCV(cv=KFold(n_splits=10, random_state=1, shuffle=True),
             estimator=ElasticNet(),
             param_grid={'alpha': [0.001, 0.01, 0.1, 0.2, 0.5, 0.9],
                         'l1_ratio': [0.001, 0.01, 0.02, 0.03, 0.04, 0.05]},
             return_train_score=True, scoring='r2')

ElasticNet()

ElasticNet()

model_cv.best_params_

{'alpha': 0.001, 'l1_ratio': 0.05}

elasticnet_model_tuned = ElasticNet(alpha=0.001, l1_ratio=0.05)
elasticnet_model_tuned.fit(x_train, y_train)

ElasticNet(alpha=0.001, l1_ratio=0.05)

ElasticNet(alpha=0.001, l1_ratio=0.05)

elasticnet_reg_tuned = model_performance_regression(elasticnet_model_tuned, x_test, y_test)
elasticnet_reg_tuned

models= pd.concat([linear_reg_test,ridge_reg,ridge_reg_tuned,lasso_reg,lasso_reg_tuned,elasticnet_reg,
                   elasticnet_reg_tuned], axis=0) #combining all models into a single dataframe
models['Models'] = ['Least Squares', 'Ridge Regression', 'Ridge Regression Tuned', 'Lasso Regression',
                                      'Lasso Regression Tuned', 'Elastic Net Regression',
                    'Elastic Net Regression Tuned'] #adding names of the models as a column to the dataframe
models = models.iloc[:,[5, 0,1,2,3,4]] #ordering names of the models as the first column
models

# Installing mlxtend library. You need to run the below code only once if mlxtend library is not previously installed.

!pip install mlxtend

Requirement already satisfied: mlxtend in /usr/local/lib/python3.10/dist-packages (0.22.0)
Requirement already satisfied: scipy>=1.2.1 in /usr/local/lib/python3.10/dist-packages (from mlxtend) (1.11.4)
Requirement already satisfied: numpy>=1.16.2 in /usr/local/lib/python3.10/dist-packages (from mlxtend) (1.25.2)
Requirement already satisfied: pandas>=0.24.2 in /usr/local/lib/python3.10/dist-packages (from mlxtend) (2.0.3)
Requirement already satisfied: scikit-learn>=1.0.2 in /usr/local/lib/python3.10/dist-packages (from mlxtend) (1.2.2)
Requirement already satisfied: matplotlib>=3.0.0 in /usr/local/lib/python3.10/dist-packages (from mlxtend) (3.7.1)
Requirement already satisfied: joblib>=0.13.2 in /usr/local/lib/python3.10/dist-packages (from mlxtend) (1.4.0)
Requirement already satisfied: setuptools in /usr/local/lib/python3.10/dist-packages (from mlxtend) (67.7.2)
Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.0.0->mlxtend) (1.2.1)
Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.0.0->mlxtend) (0.12.1)
Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.0.0->mlxtend) (4.51.0)
Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.0.0->mlxtend) (1.4.5)
Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.0.0->mlxtend) (24.0)
Requirement already satisfied: pillow>=6.2.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.0.0->mlxtend) (9.4.0)
Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.0.0->mlxtend) (3.1.2)
Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.0.0->mlxtend) (2.8.2)
Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=0.24.2->mlxtend) (2023.4)
Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=0.24.2->mlxtend) (2024.1)
Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn>=1.0.2->mlxtend) (3.5.0)
Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.7->matplotlib>=3.0.0->mlxtend) (1.16.0)

# Importing Sequential Feature Selector
from mlxtend.feature_selection import SequentialFeatureSelector as SFS

# Initializing the model to pass to SFS
reg = LinearRegression()

# Forward Feature Selection
sfs = SFS(
    reg,
    k_features=x_train.shape[1],
    forward=True,
    floating=False,
    scoring="r2",
    n_jobs=-1,
    verbose=2,
    cv=5,
)

# Perform SFS
sfs = sfs.fit(x_train, y_train)

[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  37 tasks      | elapsed:  1.2min
[Parallel(n_jobs=-1)]: Done  41 out of  41 | elapsed:  1.3min finished

[2024-05-06 08:43:34] Features: 1/41 -- score: 0.49188988610314494[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  37 tasks      | elapsed:   58.9s
[Parallel(n_jobs=-1)]: Done  40 out of  40 | elapsed:  1.1min finished

[2024-05-06 08:44:38] Features: 2/41 -- score: 0.6046160397618378[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  39 out of  39 | elapsed:  1.2min finished

[2024-05-06 08:45:48] Features: 3/41 -- score: 0.6461909142668075[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  38 out of  38 | elapsed:  1.2min finished

[2024-05-06 08:47:00] Features: 4/41 -- score: 0.7013054914238064[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  37 out of  37 | elapsed:  1.3min finished

[2024-05-06 08:48:15] Features: 5/41 -- score: 0.7323069421611198[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  36 out of  36 | elapsed:  1.3min finished

[2024-05-06 08:49:36] Features: 6/41 -- score: 0.8191351388509401[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  35 out of  35 | elapsed:  1.3min finished

[2024-05-06 08:50:57] Features: 7/41 -- score: 0.8303282862064949[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  34 out of  34 | elapsed:  1.4min finished

[2024-05-06 08:52:22] Features: 8/41 -- score: 0.8395075505200165[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  33 out of  33 | elapsed:  1.5min finished

[2024-05-06 08:53:53] Features: 9/41 -- score: 0.8406253593745727[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  32 out of  32 | elapsed:  1.5min finished

[2024-05-06 08:55:24] Features: 10/41 -- score: 0.8414600432551443[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  31 out of  31 | elapsed:  1.6min finished

[2024-05-06 08:57:01] Features: 11/41 -- score: 0.8422172722438954[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  30 out of  30 | elapsed:  1.6min finished

[2024-05-06 08:58:36] Features: 12/41 -- score: 0.8423261376358377[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  29 out of  29 | elapsed:  1.7min finished

[2024-05-06 09:00:15] Features: 13/41 -- score: 0.8423952895273421[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  28 out of  28 | elapsed:  1.9min finished

[2024-05-06 09:02:07] Features: 14/41 -- score: 0.8424554518867557[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  27 out of  27 | elapsed:  1.9min finished

[2024-05-06 09:03:58] Features: 15/41 -- score: 0.8425213613275844[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  26 out of  26 | elapsed:  1.9min finished

[2024-05-06 09:05:52] Features: 16/41 -- score: 0.8425660490400733[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  25 out of  25 | elapsed:  1.9min finished

[2024-05-06 09:07:44] Features: 17/41 -- score: 0.8426615241241737[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  24 out of  24 | elapsed:  1.9min finished

[2024-05-06 09:09:38] Features: 18/41 -- score: 0.8426866078058511[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  23 out of  23 | elapsed:  1.9min finished

[2024-05-06 09:11:33] Features: 19/41 -- score: 0.8427094423867043[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  22 out of  22 | elapsed:  2.1min finished

[2024-05-06 09:13:40] Features: 20/41 -- score: 0.8427304449567397[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  21 out of  21 | elapsed:  1.9min finished

[2024-05-06 09:15:34] Features: 21/41 -- score: 0.8427404093833673[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  20 out of  20 | elapsed:  1.9min finished

[2024-05-06 09:17:25] Features: 22/41 -- score: 0.8427505409320879[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  19 out of  19 | elapsed:  1.9min finished

[2024-05-06 09:19:18] Features: 23/41 -- score: 0.8427572335567[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  18 out of  18 | elapsed:  1.9min finished

[2024-05-06 09:21:10] Features: 24/41 -- score: 0.8427691076570655[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  17 out of  17 | elapsed:  1.9min finished

[2024-05-06 09:23:06] Features: 25/41 -- score: 0.8427740700470843[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  16 out of  16 | elapsed:  1.7min finished

[2024-05-06 09:24:49] Features: 26/41 -- score: 0.8427758697137149[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  15 out of  15 | elapsed:  1.7min finished

[2024-05-06 09:26:32] Features: 27/41 -- score: 0.8427778696285013[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  14 out of  14 | elapsed:  1.6min finished

[2024-05-06 09:28:10] Features: 28/41 -- score: 0.8427791238823727[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  13 out of  13 | elapsed:  1.6min finished

[2024-05-06 09:29:44] Features: 29/41 -- score: 0.8427807461672205[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  12 out of  12 | elapsed:  1.5min finished

[2024-05-06 09:31:16] Features: 30/41 -- score: 0.8427809322153685[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  11 out of  11 | elapsed:  1.6min finished

[2024-05-06 09:32:49] Features: 31/41 -- score: 0.8427809322153685[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  10 out of  10 | elapsed:  1.3min finished

[2024-05-06 09:34:07] Features: 32/41 -- score: 0.8427809322153685[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done   9 out of   9 | elapsed:  1.2min finished

[2024-05-06 09:35:22] Features: 33/41 -- score: 0.8427803380446244[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done   8 out of   8 | elapsed:  1.1min finished

[2024-05-06 09:36:30] Features: 34/41 -- score: 0.8427796949690372[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done   7 out of   7 | elapsed:  1.0min finished

[2024-05-06 09:37:33] Features: 35/41 -- score: 0.8427789615641776[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done   6 out of   6 | elapsed:   53.3s finished

[2024-05-06 09:38:26] Features: 36/41 -- score: 0.8427779197388698[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done   5 out of   5 | elapsed:   47.9s finished

[2024-05-06 09:39:14] Features: 37/41 -- score: 0.8427759963463547[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done   4 out of   4 | elapsed:   38.4s finished

[2024-05-06 09:39:52] Features: 38/41 -- score: 0.8427733960444744[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done   3 out of   3 | elapsed:   32.3s finished

[2024-05-06 09:40:25] Features: 39/41 -- score: 0.8427687463538682[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done   2 out of   2 | elapsed:   19.6s finished

[2024-05-06 09:40:45] Features: 40/41 -- score: 0.8427687463538682[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.

[2024-05-06 09:40:58] Features: 41/41 -- score: 0.8427687463538682

sfs.get_metric_dict()

{1: {'feature_idx': (5,),
  'cv_scores': array([0.48930483, 0.48939957, 0.49302582, 0.48922331, 0.4984959 ]),
  'avg_score': 0.49188988610314494,
  'feature_names': ('Department_gynecology',),
  'ci_bound': 0.004631493101657075,
  'std_dev': 0.0036034589801322166,
  'std_err': 0.0018017294900661083},
 2: {'feature_idx': (5, 6),
  'cv_scores': array([0.60393142, 0.60360277, 0.60160635, 0.60347042, 0.61046924]),
  'avg_score': 0.6046160397618378,
  'feature_names': ('Department_gynecology', 'Department_radiotherapy'),
  'ci_bound': 0.003903818905262394,
  'std_dev': 0.0030373037338530533,
  'std_err': 0.0015186518669265266},
 3: {'feature_idx': (5, 6, 23),
  'cv_scores': array([0.64519204, 0.6466788 , 0.64365579, 0.64406087, 0.65136707]),
  'avg_score': 0.6461909142668075,
  'feature_names': ('Department_gynecology',
   'Department_radiotherapy',
   'Age_31-40'),
  'ci_bound': 0.0035892679605198543,
  'std_dev': 0.0027925724125139285,
  'std_err': 0.0013962862062569643},
 4: {'feature_idx': (5, 6, 23, 24),
  'cv_scores': array([0.70130514, 0.70174535, 0.69909054, 0.70011695, 0.70426948]),
  'avg_score': 0.7013054914238064,
  'feature_names': ('Department_gynecology',
   'Department_radiotherapy',
   'Age_31-40',
   'Age_41-50'),
  'ci_bound': 0.0022481465718417765,
  'std_dev': 0.001749134409820941,
  'std_err': 0.0008745672049104705},
 5: {'feature_idx': (5, 6, 22, 23, 24),
  'cv_scores': array([0.73232311, 0.73311883, 0.73025991, 0.73047301, 0.73535986]),
  'avg_score': 0.7323069421611198,
  'feature_names': ('Department_gynecology',
   'Department_radiotherapy',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50'),
  'ci_bound': 0.0024068522854820544,
  'std_dev': 0.0018726128467877884,
  'std_err': 0.0009363064233938942},
 6: {'feature_idx': (5, 6, 21, 22, 23, 24),
  'cv_scores': array([0.81759505, 0.82082637, 0.81776443, 0.81792308, 0.82156676]),
  'avg_score': 0.8191351388509401,
  'feature_names': ('Department_gynecology',
   'Department_radiotherapy',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50'),
  'ci_bound': 0.00218823495067042,
  'std_dev': 0.0017025211331549424,
  'std_err': 0.0008512605665774712},
 7: {'feature_idx': (4, 5, 6, 21, 22, 23, 24),
  'cv_scores': array([0.82910903, 0.83188966, 0.82885568, 0.82915996, 0.8326271 ]),
  'avg_score': 0.8303282862064949,
  'feature_names': ('Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50'),
  'ci_bound': 0.002051848579320233,
  'std_dev': 0.0015964079027512008,
  'std_err': 0.0007982039513756004},
 8: {'feature_idx': (4, 5, 6, 7, 21, 22, 23, 24),
  'cv_scores': array([0.83841525, 0.84068   , 0.83778767, 0.83893676, 0.84171807]),
  'avg_score': 0.8395075505200165,
  'feature_names': ('Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50'),
  'ci_bound': 0.0018835514590598713,
  'std_dev': 0.0014654670255823212,
  'std_err': 0.0007327335127911606},
 9: {'feature_idx': (4, 5, 6, 7, 18, 21, 22, 23, 24),
  'cv_scores': array([0.8395841 , 0.84177861, 0.83891449, 0.84007992, 0.84276968]),
  'avg_score': 0.8406253593745727,
  'feature_names': ('Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'doctor_name_Dr Sarah',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50'),
  'ci_bound': 0.0018390805560939815,
  'std_dev': 0.0014308671522521225,
  'std_err': 0.0007154335761260613},
 10: {'feature_idx': (4, 5, 6, 7, 18, 21, 22, 23, 24, 37),
  'cv_scores': array([0.84042973, 0.84272043, 0.8397547 , 0.84087775, 0.84351761]),
  'avg_score': 0.8414600432551443,
  'feature_names': ('Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'doctor_name_Dr Sarah',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'health_conditions_Heart disease'),
  'ci_bound': 0.0018295399651148694,
  'std_dev': 0.0014234442483451405,
  'std_err': 0.0007117221241725703},
 11: {'feature_idx': (0, 4, 5, 6, 7, 18, 21, 22, 23, 24, 37),
  'cv_scores': array([0.84122914, 0.84335217, 0.84047911, 0.84174549, 0.84428045]),
  'avg_score': 0.8422172722438954,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'doctor_name_Dr Sarah',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'health_conditions_Heart disease'),
  'ci_bound': 0.0017961805756157043,
  'std_dev': 0.0013974895099866864,
  'std_err': 0.0006987447549933432},
 12: {'feature_idx': (0, 4, 5, 6, 7, 12, 18, 21, 22, 23, 24, 37),
  'cv_scores': array([0.84133146, 0.84346648, 0.84059185, 0.84183307, 0.84440783]),
  'avg_score': 0.8423261376358377,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Sarah',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'health_conditions_Heart disease'),
  'ci_bound': 0.001806196554090374,
  'std_dev': 0.001405282281515688,
  'std_err': 0.0007026411407578439},
 13: {'feature_idx': (0, 4, 5, 6, 7, 12, 18, 21, 22, 23, 24, 32, 37),
  'cv_scores': array([0.84143434, 0.84354144, 0.84068201, 0.84186707, 0.84445158]),
  'avg_score': 0.8423952895273421,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Sarah',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Type of Admission_Trauma',
   'health_conditions_Heart disease'),
  'ci_bound': 0.0017883348234278233,
  'std_dev': 0.0013913852482385265,
  'std_err': 0.0006956926241192632},
 14: {'feature_idx': (0, 4, 5, 6, 7, 11, 12, 18, 21, 22, 23, 24, 32, 37),
  'cv_scores': array([0.84149253, 0.84359962, 0.84074705, 0.84189538, 0.84454268]),
  'avg_score': 0.8424554518867557,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Sarah',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Type of Admission_Trauma',
   'health_conditions_Heart disease'),
  'ci_bound': 0.0018017191642011664,
  'std_dev': 0.001401798720070234,
  'std_err': 0.0007008993600351169},
 15: {'feature_idx': (0, 4, 5, 6, 7, 9, 11, 12, 18, 21, 22, 23, 24, 32, 37),
  'cv_scores': array([0.84151756, 0.84365472, 0.84083538, 0.84196472, 0.84463442]),
  'avg_score': 0.8425213613275844,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Sarah',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Type of Admission_Trauma',
   'health_conditions_Heart disease'),
  'ci_bound': 0.0018094336278431788,
  'std_dev': 0.0014078008348694048,
  'std_err': 0.0007039004174347023},
 16: {'feature_idx': (0,
   4,
   5,
   6,
   7,
   9,
   11,
   12,
   18,
   20,
   21,
   22,
   23,
   24,
   32,
   37),
  'cv_scores': array([0.84157076, 0.84368731, 0.84088641, 0.84200681, 0.84467896]),
  'avg_score': 0.8425660490400733,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Type of Admission_Trauma',
   'health_conditions_Heart disease'),
  'ci_bound': 0.0018036427274464757,
  'std_dev': 0.00140329531762485,
  'std_err': 0.0007016476588124251},
 17: {'feature_idx': (0,
   4,
   5,
   6,
   7,
   9,
   11,
   12,
   18,
   20,
   21,
   22,
   23,
   24,
   32,
   36,
   37),
  'cv_scores': array([0.84163027, 0.84381662, 0.8409956 , 0.84209143, 0.84477371]),
  'avg_score': 0.8426615241241737,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Type of Admission_Trauma',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease'),
  'ci_bound': 0.00181397721035091,
  'std_dev': 0.0014113358964208509,
  'std_err': 0.0007056679482104253},
 18: {'feature_idx': (0,
   4,
   5,
   6,
   7,
   9,
   11,
   12,
   18,
   20,
   21,
   22,
   23,
   24,
   32,
   33,
   36,
   37),
  'cv_scores': array([0.84165314, 0.84383133, 0.84104803, 0.84211931, 0.84478123]),
  'avg_score': 0.8426866078058511,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease'),
  'ci_bound': 0.0017968945257366444,
  'std_dev': 0.0013980449874360099,
  'std_err': 0.0006990224937180049},
 19: {'feature_idx': (0,
   3,
   4,
   5,
   6,
   7,
   9,
   11,
   12,
   18,
   20,
   21,
   22,
   23,
   24,
   32,
   33,
   36,
   37),
  'cv_scores': array([0.84165556, 0.84387059, 0.8410869 , 0.84214295, 0.84479122]),
  'avg_score': 0.8427094423867043,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease'),
  'ci_bound': 0.0017944661334763027,
  'std_dev': 0.0013961556157569975,
  'std_err': 0.0006980778078784988},
 20: {'feature_idx': (0,
   3,
   4,
   5,
   6,
   7,
   9,
   11,
   12,
   18,
   20,
   21,
   22,
   23,
   24,
   28,
   32,
   33,
   36,
   37),
  'cv_scores': array([0.84169653, 0.84389602, 0.84109857, 0.84214173, 0.84481937]),
  'avg_score': 0.8427304449567397,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_81-90',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease'),
  'ci_bound': 0.0017994745127761138,
  'std_dev': 0.0014000523050033567,
  'std_err': 0.0007000261525016782},
 21: {'feature_idx': (0,
   3,
   4,
   5,
   6,
   7,
   9,
   11,
   12,
   18,
   20,
   21,
   22,
   23,
   24,
   26,
   28,
   32,
   33,
   36,
   37),
  'cv_scores': array([0.84171921, 0.84389189, 0.84112059, 0.84214082, 0.84482953]),
  'avg_score': 0.8427404093833673,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_61-70',
   'Age_81-90',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease'),
  'ci_bound': 0.001791726954504796,
  'std_dev': 0.001394024441458253,
  'std_err': 0.0006970122207291264},
 22: {'feature_idx': (0,
   3,
   4,
   5,
   6,
   7,
   9,
   11,
   12,
   18,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   28,
   32,
   33,
   36,
   37),
  'cv_scores': array([0.84172767, 0.84391208, 0.84112203, 0.84215577, 0.84483515]),
  'avg_score': 0.8427505409320879,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_81-90',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease'),
  'ci_bound': 0.0017945182676311698,
  'std_dev': 0.0013961961779006527,
  'std_err': 0.0006980980889503263},
 23: {'feature_idx': (0,
   3,
   4,
   5,
   6,
   7,
   9,
   11,
   12,
   15,
   18,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   28,
   32,
   33,
   36,
   37),
  'cv_scores': array([0.84173583, 0.84392189, 0.84113036, 0.84216222, 0.84483587]),
  'avg_score': 0.8427572335567,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_81-90',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease'),
  'ci_bound': 0.0017921537624081036,
  'std_dev': 0.0013943565125070934,
  'std_err': 0.0006971782562535467},
 24: {'feature_idx': (0,
   3,
   4,
   5,
   6,
   7,
   9,
   11,
   12,
   15,
   18,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   28,
   32,
   33,
   35,
   36,
   37),
  'cv_scores': array([0.84174792, 0.84392579, 0.84114267, 0.84217859, 0.84485057]),
  'avg_score': 0.8427691076570655,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_81-90',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease'),
  'ci_bound': 0.0017908723320688754,
  'std_dev': 0.0013933595161687736,
  'std_err': 0.0006966797580843868},
 25: {'feature_idx': (0,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   11,
   12,
   15,
   18,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   28,
   32,
   33,
   35,
   36,
   37),
  'cv_scores': array([0.84175575, 0.84392909, 0.84114694, 0.84217963, 0.84485894]),
  'avg_score': 0.8427740700470843,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_81-90',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease'),
  'ci_bound': 0.0017919222433743585,
  'std_dev': 0.0013941763828333774,
  'std_err': 0.0006970881914166886},
 26: {'feature_idx': (0,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   11,
   12,
   15,
   18,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   32,
   33,
   35,
   36,
   37),
  'cv_scores': array([0.84176058, 0.84392785, 0.84114221, 0.84218609, 0.84486261]),
  'avg_score': 0.8427758697137149,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease'),
  'ci_bound': 0.0017928808477604453,
  'std_dev': 0.0013949222096126944,
  'std_err': 0.0006974611048063472},
 27: {'feature_idx': (0,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   11,
   12,
   15,
   18,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   29,
   32,
   33,
   35,
   36,
   37),
  'cv_scores': array([0.84175977, 0.84393144, 0.8411444 , 0.84218713, 0.84486661]),
  'avg_score': 0.8427778696285013,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Age_91-100',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease'),
  'ci_bound': 0.0017945631293705157,
  'std_dev': 0.0013962310818579646,
  'std_err': 0.0006981155409289823},
 28: {'feature_idx': (0,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   11,
   12,
   15,
   18,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   29,
   32,
   33,
   35,
   36,
   37,
   38),
  'cv_scores': array([0.84175803, 0.84393421, 0.8411476 , 0.8421875 , 0.84486829]),
  'avg_score': 0.8427791238823727,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Age_91-100',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease',
   'health_conditions_High Blood Pressure'),
  'ci_bound': 0.001795122470303991,
  'std_dev': 0.0013966662681068583,
  'std_err': 0.0006983331340534291},
 29: {'feature_idx': (0,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   11,
   12,
   15,
   18,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   29,
   32,
   33,
   34,
   35,
   36,
   37,
   38),
  'cv_scores': array([0.84176298, 0.84393899, 0.84113744, 0.84219395, 0.84487037]),
  'avg_score': 0.8427807461672205,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Age_91-100',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Minor',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease',
   'health_conditions_High Blood Pressure'),
  'ci_bound': 0.0017983700228782758,
  'std_dev': 0.0013991929743396865,
  'std_err': 0.0006995964871698432},
 30: {'feature_idx': (0,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   11,
   12,
   15,
   18,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   29,
   32,
   33,
   34,
   35,
   36,
   37,
   38,
   40),
  'cv_scores': array([0.84176214, 0.84393978, 0.84113795, 0.84219458, 0.84487021]),
  'avg_score': 0.8427809322153685,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Age_91-100',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Minor',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease',
   'health_conditions_High Blood Pressure',
   'Insurance_Yes'),
  'ci_bound': 0.0017984071199195594,
  'std_dev': 0.0013992218370981139,
  'std_err': 0.0006996109185490568},
 31: {'feature_idx': (0,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   10,
   11,
   12,
   15,
   18,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   29,
   32,
   33,
   34,
   35,
   36,
   37,
   38,
   40),
  'cv_scores': array([0.84176214, 0.84393978, 0.84113795, 0.84219458, 0.84487021]),
  'avg_score': 0.8427809322153685,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_D',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Age_91-100',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Minor',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease',
   'health_conditions_High Blood Pressure',
   'Insurance_Yes'),
  'ci_bound': 0.0017984071199195896,
  'std_dev': 0.0013992218370981369,
  'std_err': 0.0006996109185490685},
 32: {'feature_idx': (0,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   10,
   11,
   12,
   15,
   16,
   18,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   29,
   32,
   33,
   34,
   35,
   36,
   37,
   38,
   40),
  'cv_scores': array([0.84176214, 0.84393978, 0.84113795, 0.84219458, 0.84487021]),
  'avg_score': 0.8427809322153685,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_D',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Olivia',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Age_91-100',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Minor',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease',
   'health_conditions_High Blood Pressure',
   'Insurance_Yes'),
  'ci_bound': 0.001798407119919604,
  'std_dev': 0.0013992218370981484,
  'std_err': 0.0006996109185490742},
 33: {'feature_idx': (0,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   10,
   11,
   12,
   15,
   16,
   17,
   18,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   29,
   32,
   33,
   34,
   35,
   36,
   37,
   38,
   40),
  'cv_scores': array([0.84176243, 0.84394197, 0.84113616, 0.84218883, 0.8448723 ]),
  'avg_score': 0.8427803380446244,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_D',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Olivia',
   'doctor_name_Dr Sam',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Age_91-100',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Minor',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease',
   'health_conditions_High Blood Pressure',
   'Insurance_Yes'),
  'ci_bound': 0.0018007868937655249,
  'std_dev': 0.0014010733819990139,
  'std_err': 0.0007005366909995069},
 34: {'feature_idx': (0,
   2,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   10,
   11,
   12,
   15,
   16,
   17,
   18,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   29,
   32,
   33,
   34,
   35,
   36,
   37,
   38,
   40),
  'cv_scores': array([0.84176239, 0.84394137, 0.84113397, 0.84218859, 0.84487215]),
  'avg_score': 0.8427796949690372,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Visitors with Patient',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_D',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Olivia',
   'doctor_name_Dr Sam',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Age_91-100',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Minor',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease',
   'health_conditions_High Blood Pressure',
   'Insurance_Yes'),
  'ci_bound': 0.0018012958615181624,
  'std_dev': 0.0014014693762018733,
  'std_err': 0.0007007346881009366},
 35: {'feature_idx': (0,
   1,
   2,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   10,
   11,
   12,
   15,
   16,
   17,
   18,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   29,
   32,
   33,
   34,
   35,
   36,
   37,
   38,
   40),
  'cv_scores': array([0.84176142, 0.84394176, 0.84113311, 0.84218763, 0.8448709 ]),
  'avg_score': 0.8427789615641776,
  'feature_names': ('Available Extra Rooms in Hospital',
   'staff_available',
   'Visitors with Patient',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_D',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Olivia',
   'doctor_name_Dr Sam',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Age_91-100',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Minor',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease',
   'health_conditions_High Blood Pressure',
   'Insurance_Yes'),
  'ci_bound': 0.0018014433625029125,
  'std_dev': 0.0014015841369791023,
  'std_err': 0.000700792068489551},
 36: {'feature_idx': (0,
   1,
   2,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   10,
   11,
   12,
   15,
   16,
   17,
   18,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   29,
   32,
   33,
   34,
   35,
   36,
   37,
   38,
   39,
   40),
  'cv_scores': array([0.84175766, 0.84394198, 0.84113194, 0.84218758, 0.84487043]),
  'avg_score': 0.8427779197388698,
  'feature_names': ('Available Extra Rooms in Hospital',
   'staff_available',
   'Visitors with Patient',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_D',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Olivia',
   'doctor_name_Dr Sam',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Age_91-100',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Minor',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease',
   'health_conditions_High Blood Pressure',
   'health_conditions_Other',
   'Insurance_Yes'),
  'ci_bound': 0.0018023700056068854,
  'std_dev': 0.0014023050967951049,
  'std_err': 0.0007011525483975524},
 37: {'feature_idx': (0,
   1,
   2,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   10,
   11,
   12,
   15,
   16,
   17,
   18,
   19,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   29,
   32,
   33,
   34,
   35,
   36,
   37,
   38,
   39,
   40),
  'cv_scores': array([0.8417447 , 0.84394054, 0.8411334 , 0.84218957, 0.84487178]),
  'avg_score': 0.8427759963463547,
  'feature_names': ('Available Extra Rooms in Hospital',
   'staff_available',
   'Visitors with Patient',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_D',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Olivia',
   'doctor_name_Dr Sam',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Simon',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Age_91-100',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Minor',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease',
   'health_conditions_High Blood Pressure',
   'health_conditions_Other',
   'Insurance_Yes'),
  'ci_bound': 0.00180436460146003,
  'std_dev': 0.0014038569601318282,
  'std_err': 0.0007019284800659141},
 38: {'feature_idx': (0,
   1,
   2,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   10,
   11,
   12,
   15,
   16,
   17,
   18,
   19,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   29,
   31,
   32,
   33,
   34,
   35,
   36,
   37,
   38,
   39,
   40),
  'cv_scores': array([0.8417445 , 0.84393137, 0.84113339, 0.84218943, 0.84486828]),
  'avg_score': 0.8427733960444744,
  'feature_names': ('Available Extra Rooms in Hospital',
   'staff_available',
   'Visitors with Patient',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_D',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Olivia',
   'doctor_name_Dr Sam',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Simon',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Age_91-100',
   'gender_Other',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Minor',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease',
   'health_conditions_High Blood Pressure',
   'health_conditions_Other',
   'Insurance_Yes'),
  'ci_bound': 0.0018011225528318932,
  'std_dev': 0.0014013345361560902,
  'std_err': 0.0007006672680780451},
 39: {'feature_idx': (0,
   1,
   2,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   10,
   11,
   12,
   13,
   15,
   16,
   17,
   18,
   19,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   29,
   31,
   32,
   33,
   34,
   35,
   36,
   37,
   38,
   39,
   40),
  'cv_scores': array([0.84174483, 0.84393285, 0.84112937, 0.84218622, 0.84485046]),
  'avg_score': 0.8427687463538682,
  'feature_names': ('Available Extra Rooms in Hospital',
   'staff_available',
   'Visitors with Patient',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_D',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr John',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Olivia',
   'doctor_name_Dr Sam',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Simon',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Age_91-100',
   'gender_Other',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Minor',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease',
   'health_conditions_High Blood Pressure',
   'health_conditions_Other',
   'Insurance_Yes'),
  'ci_bound': 0.0017960998677658592,
  'std_dev': 0.0013974267165375962,
  'std_err': 0.000698713358268798},
 40: {'feature_idx': (0,
   1,
   2,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   10,
   11,
   12,
   13,
   14,
   15,
   16,
   17,
   18,
   19,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   29,
   31,
   32,
   33,
   34,
   35,
   36,
   37,
   38,
   39,
   40),
  'cv_scores': array([0.84174483, 0.84393285, 0.84112937, 0.84218622, 0.84485046]),
  'avg_score': 0.8427687463538682,
  'feature_names': ('Available Extra Rooms in Hospital',
   'staff_available',
   'Visitors with Patient',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_D',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr John',
   'doctor_name_Dr Mark',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Olivia',
   'doctor_name_Dr Sam',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Simon',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Age_91-100',
   'gender_Other',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Minor',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease',
   'health_conditions_High Blood Pressure',
   'health_conditions_Other',
   'Insurance_Yes'),
  'ci_bound': 0.0017960998677658809,
  'std_dev': 0.001397426716537613,
  'std_err': 0.0006987133582688064},
 41: {'feature_idx': (0,
   1,
   2,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   10,
   11,
   12,
   13,
   14,
   15,
   16,
   17,
   18,
   19,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   29,
   30,
   31,
   32,
   33,
   34,
   35,
   36,
   37,
   38,
   39,
   40),
  'cv_scores': array([0.84174483, 0.84393285, 0.84112937, 0.84218622, 0.84485046]),
  'avg_score': 0.8427687463538682,
  'feature_names': ('Available Extra Rooms in Hospital',
   'staff_available',
   'Visitors with Patient',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_D',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr John',
   'doctor_name_Dr Mark',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Olivia',
   'doctor_name_Dr Sam',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Simon',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Age_91-100',
   'gender_Male',
   'gender_Other',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Minor',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease',
   'health_conditions_High Blood Pressure',
   'health_conditions_Other',
   'Insurance_Yes'),
  'ci_bound': 0.0017960998677653498,
  'std_dev': 0.0013974267165371996,
  'std_err': 0.0006987133582685998}}

# To plot the performance of the model with addition of each feature
from mlxtend.plotting import plot_sequential_feature_selection as plot_sfs

fig1 = plot_sfs(sfs.get_metric_dict(), kind="std_err", figsize=(15, 5))
plt.title("Sequential Forward Selection")
plt.xticks(rotation=90)
plt.show()

sfs.get_metric_dict()

{1: {'feature_idx': (5,),
  'cv_scores': array([0.48930483, 0.48939957, 0.49302582, 0.48922331, 0.4984959 ]),
  'avg_score': 0.49188988610314494,
  'feature_names': ('Department_gynecology',),
  'ci_bound': 0.004631493101657075,
  'std_dev': 0.0036034589801322166,
  'std_err': 0.0018017294900661083},
 2: {'feature_idx': (5, 6),
  'cv_scores': array([0.60393142, 0.60360277, 0.60160635, 0.60347042, 0.61046924]),
  'avg_score': 0.6046160397618378,
  'feature_names': ('Department_gynecology', 'Department_radiotherapy'),
  'ci_bound': 0.003903818905262394,
  'std_dev': 0.0030373037338530533,
  'std_err': 0.0015186518669265266},
 3: {'feature_idx': (5, 6, 23),
  'cv_scores': array([0.64519204, 0.6466788 , 0.64365579, 0.64406087, 0.65136707]),
  'avg_score': 0.6461909142668075,
  'feature_names': ('Department_gynecology',
   'Department_radiotherapy',
   'Age_31-40'),
  'ci_bound': 0.0035892679605198543,
  'std_dev': 0.0027925724125139285,
  'std_err': 0.0013962862062569643},
 4: {'feature_idx': (5, 6, 23, 24),
  'cv_scores': array([0.70130514, 0.70174535, 0.69909054, 0.70011695, 0.70426948]),
  'avg_score': 0.7013054914238064,
  'feature_names': ('Department_gynecology',
   'Department_radiotherapy',
   'Age_31-40',
   'Age_41-50'),
  'ci_bound': 0.0022481465718417765,
  'std_dev': 0.001749134409820941,
  'std_err': 0.0008745672049104705},
 5: {'feature_idx': (5, 6, 22, 23, 24),
  'cv_scores': array([0.73232311, 0.73311883, 0.73025991, 0.73047301, 0.73535986]),
  'avg_score': 0.7323069421611198,
  'feature_names': ('Department_gynecology',
   'Department_radiotherapy',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50'),
  'ci_bound': 0.0024068522854820544,
  'std_dev': 0.0018726128467877884,
  'std_err': 0.0009363064233938942},
 6: {'feature_idx': (5, 6, 21, 22, 23, 24),
  'cv_scores': array([0.81759505, 0.82082637, 0.81776443, 0.81792308, 0.82156676]),
  'avg_score': 0.8191351388509401,
  'feature_names': ('Department_gynecology',
   'Department_radiotherapy',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50'),
  'ci_bound': 0.00218823495067042,
  'std_dev': 0.0017025211331549424,
  'std_err': 0.0008512605665774712},
 7: {'feature_idx': (4, 5, 6, 21, 22, 23, 24),
  'cv_scores': array([0.82910903, 0.83188966, 0.82885568, 0.82915996, 0.8326271 ]),
  'avg_score': 0.8303282862064949,
  'feature_names': ('Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50'),
  'ci_bound': 0.002051848579320233,
  'std_dev': 0.0015964079027512008,
  'std_err': 0.0007982039513756004},
 8: {'feature_idx': (4, 5, 6, 7, 21, 22, 23, 24),
  'cv_scores': array([0.83841525, 0.84068   , 0.83778767, 0.83893676, 0.84171807]),
  'avg_score': 0.8395075505200165,
  'feature_names': ('Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50'),
  'ci_bound': 0.0018835514590598713,
  'std_dev': 0.0014654670255823212,
  'std_err': 0.0007327335127911606},
 9: {'feature_idx': (4, 5, 6, 7, 18, 21, 22, 23, 24),
  'cv_scores': array([0.8395841 , 0.84177861, 0.83891449, 0.84007992, 0.84276968]),
  'avg_score': 0.8406253593745727,
  'feature_names': ('Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'doctor_name_Dr Sarah',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50'),
  'ci_bound': 0.0018390805560939815,
  'std_dev': 0.0014308671522521225,
  'std_err': 0.0007154335761260613},
 10: {'feature_idx': (4, 5, 6, 7, 18, 21, 22, 23, 24, 37),
  'cv_scores': array([0.84042973, 0.84272043, 0.8397547 , 0.84087775, 0.84351761]),
  'avg_score': 0.8414600432551443,
  'feature_names': ('Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'doctor_name_Dr Sarah',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'health_conditions_Heart disease'),
  'ci_bound': 0.0018295399651148694,
  'std_dev': 0.0014234442483451405,
  'std_err': 0.0007117221241725703},
 11: {'feature_idx': (0, 4, 5, 6, 7, 18, 21, 22, 23, 24, 37),
  'cv_scores': array([0.84122914, 0.84335217, 0.84047911, 0.84174549, 0.84428045]),
  'avg_score': 0.8422172722438954,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'doctor_name_Dr Sarah',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'health_conditions_Heart disease'),
  'ci_bound': 0.0017961805756157043,
  'std_dev': 0.0013974895099866864,
  'std_err': 0.0006987447549933432},
 12: {'feature_idx': (0, 4, 5, 6, 7, 12, 18, 21, 22, 23, 24, 37),
  'cv_scores': array([0.84133146, 0.84346648, 0.84059185, 0.84183307, 0.84440783]),
  'avg_score': 0.8423261376358377,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Sarah',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'health_conditions_Heart disease'),
  'ci_bound': 0.001806196554090374,
  'std_dev': 0.001405282281515688,
  'std_err': 0.0007026411407578439},
 13: {'feature_idx': (0, 4, 5, 6, 7, 12, 18, 21, 22, 23, 24, 32, 37),
  'cv_scores': array([0.84143434, 0.84354144, 0.84068201, 0.84186707, 0.84445158]),
  'avg_score': 0.8423952895273421,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Sarah',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Type of Admission_Trauma',
   'health_conditions_Heart disease'),
  'ci_bound': 0.0017883348234278233,
  'std_dev': 0.0013913852482385265,
  'std_err': 0.0006956926241192632},
 14: {'feature_idx': (0, 4, 5, 6, 7, 11, 12, 18, 21, 22, 23, 24, 32, 37),
  'cv_scores': array([0.84149253, 0.84359962, 0.84074705, 0.84189538, 0.84454268]),
  'avg_score': 0.8424554518867557,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Sarah',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Type of Admission_Trauma',
   'health_conditions_Heart disease'),
  'ci_bound': 0.0018017191642011664,
  'std_dev': 0.001401798720070234,
  'std_err': 0.0007008993600351169},
 15: {'feature_idx': (0, 4, 5, 6, 7, 9, 11, 12, 18, 21, 22, 23, 24, 32, 37),
  'cv_scores': array([0.84151756, 0.84365472, 0.84083538, 0.84196472, 0.84463442]),
  'avg_score': 0.8425213613275844,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Sarah',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Type of Admission_Trauma',
   'health_conditions_Heart disease'),
  'ci_bound': 0.0018094336278431788,
  'std_dev': 0.0014078008348694048,
  'std_err': 0.0007039004174347023},
 16: {'feature_idx': (0,
   4,
   5,
   6,
   7,
   9,
   11,
   12,
   18,
   20,
   21,
   22,
   23,
   24,
   32,
   37),
  'cv_scores': array([0.84157076, 0.84368731, 0.84088641, 0.84200681, 0.84467896]),
  'avg_score': 0.8425660490400733,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Type of Admission_Trauma',
   'health_conditions_Heart disease'),
  'ci_bound': 0.0018036427274464757,
  'std_dev': 0.00140329531762485,
  'std_err': 0.0007016476588124251},
 17: {'feature_idx': (0,
   4,
   5,
   6,
   7,
   9,
   11,
   12,
   18,
   20,
   21,
   22,
   23,
   24,
   32,
   36,
   37),
  'cv_scores': array([0.84163027, 0.84381662, 0.8409956 , 0.84209143, 0.84477371]),
  'avg_score': 0.8426615241241737,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Type of Admission_Trauma',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease'),
  'ci_bound': 0.00181397721035091,
  'std_dev': 0.0014113358964208509,
  'std_err': 0.0007056679482104253},
 18: {'feature_idx': (0,
   4,
   5,
   6,
   7,
   9,
   11,
   12,
   18,
   20,
   21,
   22,
   23,
   24,
   32,
   33,
   36,
   37),
  'cv_scores': array([0.84165314, 0.84383133, 0.84104803, 0.84211931, 0.84478123]),
  'avg_score': 0.8426866078058511,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease'),
  'ci_bound': 0.0017968945257366444,
  'std_dev': 0.0013980449874360099,
  'std_err': 0.0006990224937180049},
 19: {'feature_idx': (0,
   3,
   4,
   5,
   6,
   7,
   9,
   11,
   12,
   18,
   20,
   21,
   22,
   23,
   24,
   32,
   33,
   36,
   37),
  'cv_scores': array([0.84165556, 0.84387059, 0.8410869 , 0.84214295, 0.84479122]),
  'avg_score': 0.8427094423867043,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease'),
  'ci_bound': 0.0017944661334763027,
  'std_dev': 0.0013961556157569975,
  'std_err': 0.0006980778078784988},
 20: {'feature_idx': (0,
   3,
   4,
   5,
   6,
   7,
   9,
   11,
   12,
   18,
   20,
   21,
   22,
   23,
   24,
   28,
   32,
   33,
   36,
   37),
  'cv_scores': array([0.84169653, 0.84389602, 0.84109857, 0.84214173, 0.84481937]),
  'avg_score': 0.8427304449567397,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_81-90',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease'),
  'ci_bound': 0.0017994745127761138,
  'std_dev': 0.0014000523050033567,
  'std_err': 0.0007000261525016782},
 21: {'feature_idx': (0,
   3,
   4,
   5,
   6,
   7,
   9,
   11,
   12,
   18,
   20,
   21,
   22,
   23,
   24,
   26,
   28,
   32,
   33,
   36,
   37),
  'cv_scores': array([0.84171921, 0.84389189, 0.84112059, 0.84214082, 0.84482953]),
  'avg_score': 0.8427404093833673,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_61-70',
   'Age_81-90',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease'),
  'ci_bound': 0.001791726954504796,
  'std_dev': 0.001394024441458253,
  'std_err': 0.0006970122207291264},
 22: {'feature_idx': (0,
   3,
   4,
   5,
   6,
   7,
   9,
   11,
   12,
   18,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   28,
   32,
   33,
   36,
   37),
  'cv_scores': array([0.84172767, 0.84391208, 0.84112203, 0.84215577, 0.84483515]),
  'avg_score': 0.8427505409320879,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_81-90',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease'),
  'ci_bound': 0.0017945182676311698,
  'std_dev': 0.0013961961779006527,
  'std_err': 0.0006980980889503263},
 23: {'feature_idx': (0,
   3,
   4,
   5,
   6,
   7,
   9,
   11,
   12,
   15,
   18,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   28,
   32,
   33,
   36,
   37),
  'cv_scores': array([0.84173583, 0.84392189, 0.84113036, 0.84216222, 0.84483587]),
  'avg_score': 0.8427572335567,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_81-90',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease'),
  'ci_bound': 0.0017921537624081036,
  'std_dev': 0.0013943565125070934,
  'std_err': 0.0006971782562535467},
 24: {'feature_idx': (0,
   3,
   4,
   5,
   6,
   7,
   9,
   11,
   12,
   15,
   18,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   28,
   32,
   33,
   35,
   36,
   37),
  'cv_scores': array([0.84174792, 0.84392579, 0.84114267, 0.84217859, 0.84485057]),
  'avg_score': 0.8427691076570655,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_81-90',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease'),
  'ci_bound': 0.0017908723320688754,
  'std_dev': 0.0013933595161687736,
  'std_err': 0.0006966797580843868},
 25: {'feature_idx': (0,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   11,
   12,
   15,
   18,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   28,
   32,
   33,
   35,
   36,
   37),
  'cv_scores': array([0.84175575, 0.84392909, 0.84114694, 0.84217963, 0.84485894]),
  'avg_score': 0.8427740700470843,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_81-90',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease'),
  'ci_bound': 0.0017919222433743585,
  'std_dev': 0.0013941763828333774,
  'std_err': 0.0006970881914166886},
 26: {'feature_idx': (0,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   11,
   12,
   15,
   18,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   32,
   33,
   35,
   36,
   37),
  'cv_scores': array([0.84176058, 0.84392785, 0.84114221, 0.84218609, 0.84486261]),
  'avg_score': 0.8427758697137149,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease'),
  'ci_bound': 0.0017928808477604453,
  'std_dev': 0.0013949222096126944,
  'std_err': 0.0006974611048063472},
 27: {'feature_idx': (0,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   11,
   12,
   15,
   18,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   29,
   32,
   33,
   35,
   36,
   37),
  'cv_scores': array([0.84175977, 0.84393144, 0.8411444 , 0.84218713, 0.84486661]),
  'avg_score': 0.8427778696285013,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Age_91-100',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease'),
  'ci_bound': 0.0017945631293705157,
  'std_dev': 0.0013962310818579646,
  'std_err': 0.0006981155409289823},
 28: {'feature_idx': (0,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   11,
   12,
   15,
   18,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   29,
   32,
   33,
   35,
   36,
   37,
   38),
  'cv_scores': array([0.84175803, 0.84393421, 0.8411476 , 0.8421875 , 0.84486829]),
  'avg_score': 0.8427791238823727,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Age_91-100',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease',
   'health_conditions_High Blood Pressure'),
  'ci_bound': 0.001795122470303991,
  'std_dev': 0.0013966662681068583,
  'std_err': 0.0006983331340534291},
 29: {'feature_idx': (0,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   11,
   12,
   15,
   18,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   29,
   32,
   33,
   34,
   35,
   36,
   37,
   38),
  'cv_scores': array([0.84176298, 0.84393899, 0.84113744, 0.84219395, 0.84487037]),
  'avg_score': 0.8427807461672205,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Age_91-100',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Minor',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease',
   'health_conditions_High Blood Pressure'),
  'ci_bound': 0.0017983700228782758,
  'std_dev': 0.0013991929743396865,
  'std_err': 0.0006995964871698432},
 30: {'feature_idx': (0,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   11,
   12,
   15,
   18,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   29,
   32,
   33,
   34,
   35,
   36,
   37,
   38,
   40),
  'cv_scores': array([0.84176214, 0.84393978, 0.84113795, 0.84219458, 0.84487021]),
  'avg_score': 0.8427809322153685,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Age_91-100',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Minor',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease',
   'health_conditions_High Blood Pressure',
   'Insurance_Yes'),
  'ci_bound': 0.0017984071199195594,
  'std_dev': 0.0013992218370981139,
  'std_err': 0.0006996109185490568},
 31: {'feature_idx': (0,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   10,
   11,
   12,
   15,
   18,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   29,
   32,
   33,
   34,
   35,
   36,
   37,
   38,
   40),
  'cv_scores': array([0.84176214, 0.84393978, 0.84113795, 0.84219458, 0.84487021]),
  'avg_score': 0.8427809322153685,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_D',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Age_91-100',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Minor',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease',
   'health_conditions_High Blood Pressure',
   'Insurance_Yes'),
  'ci_bound': 0.0017984071199195896,
  'std_dev': 0.0013992218370981369,
  'std_err': 0.0006996109185490685},
 32: {'feature_idx': (0,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   10,
   11,
   12,
   15,
   16,
   18,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   29,
   32,
   33,
   34,
   35,
   36,
   37,
   38,
   40),
  'cv_scores': array([0.84176214, 0.84393978, 0.84113795, 0.84219458, 0.84487021]),
  'avg_score': 0.8427809322153685,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_D',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Olivia',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Age_91-100',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Minor',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease',
   'health_conditions_High Blood Pressure',
   'Insurance_Yes'),
  'ci_bound': 0.001798407119919604,
  'std_dev': 0.0013992218370981484,
  'std_err': 0.0006996109185490742},
 33: {'feature_idx': (0,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   10,
   11,
   12,
   15,
   16,
   17,
   18,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   29,
   32,
   33,
   34,
   35,
   36,
   37,
   38,
   40),
  'cv_scores': array([0.84176243, 0.84394197, 0.84113616, 0.84218883, 0.8448723 ]),
  'avg_score': 0.8427803380446244,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_D',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Olivia',
   'doctor_name_Dr Sam',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Age_91-100',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Minor',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease',
   'health_conditions_High Blood Pressure',
   'Insurance_Yes'),
  'ci_bound': 0.0018007868937655249,
  'std_dev': 0.0014010733819990139,
  'std_err': 0.0007005366909995069},
 34: {'feature_idx': (0,
   2,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   10,
   11,
   12,
   15,
   16,
   17,
   18,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   29,
   32,
   33,
   34,
   35,
   36,
   37,
   38,
   40),
  'cv_scores': array([0.84176239, 0.84394137, 0.84113397, 0.84218859, 0.84487215]),
  'avg_score': 0.8427796949690372,
  'feature_names': ('Available Extra Rooms in Hospital',
   'Visitors with Patient',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_D',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Olivia',
   'doctor_name_Dr Sam',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Age_91-100',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Minor',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease',
   'health_conditions_High Blood Pressure',
   'Insurance_Yes'),
  'ci_bound': 0.0018012958615181624,
  'std_dev': 0.0014014693762018733,
  'std_err': 0.0007007346881009366},
 35: {'feature_idx': (0,
   1,
   2,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   10,
   11,
   12,
   15,
   16,
   17,
   18,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   29,
   32,
   33,
   34,
   35,
   36,
   37,
   38,
   40),
  'cv_scores': array([0.84176142, 0.84394176, 0.84113311, 0.84218763, 0.8448709 ]),
  'avg_score': 0.8427789615641776,
  'feature_names': ('Available Extra Rooms in Hospital',
   'staff_available',
   'Visitors with Patient',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_D',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Olivia',
   'doctor_name_Dr Sam',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Age_91-100',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Minor',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease',
   'health_conditions_High Blood Pressure',
   'Insurance_Yes'),
  'ci_bound': 0.0018014433625029125,
  'std_dev': 0.0014015841369791023,
  'std_err': 0.000700792068489551},
 36: {'feature_idx': (0,
   1,
   2,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   10,
   11,
   12,
   15,
   16,
   17,
   18,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   29,
   32,
   33,
   34,
   35,
   36,
   37,
   38,
   39,
   40),
  'cv_scores': array([0.84175766, 0.84394198, 0.84113194, 0.84218758, 0.84487043]),
  'avg_score': 0.8427779197388698,
  'feature_names': ('Available Extra Rooms in Hospital',
   'staff_available',
   'Visitors with Patient',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_D',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Olivia',
   'doctor_name_Dr Sam',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Age_91-100',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Minor',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease',
   'health_conditions_High Blood Pressure',
   'health_conditions_Other',
   'Insurance_Yes'),
  'ci_bound': 0.0018023700056068854,
  'std_dev': 0.0014023050967951049,
  'std_err': 0.0007011525483975524},
 37: {'feature_idx': (0,
   1,
   2,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   10,
   11,
   12,
   15,
   16,
   17,
   18,
   19,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   29,
   32,
   33,
   34,
   35,
   36,
   37,
   38,
   39,
   40),
  'cv_scores': array([0.8417447 , 0.84394054, 0.8411334 , 0.84218957, 0.84487178]),
  'avg_score': 0.8427759963463547,
  'feature_names': ('Available Extra Rooms in Hospital',
   'staff_available',
   'Visitors with Patient',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_D',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Olivia',
   'doctor_name_Dr Sam',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Simon',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Age_91-100',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Minor',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease',
   'health_conditions_High Blood Pressure',
   'health_conditions_Other',
   'Insurance_Yes'),
  'ci_bound': 0.00180436460146003,
  'std_dev': 0.0014038569601318282,
  'std_err': 0.0007019284800659141},
 38: {'feature_idx': (0,
   1,
   2,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   10,
   11,
   12,
   15,
   16,
   17,
   18,
   19,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   29,
   31,
   32,
   33,
   34,
   35,
   36,
   37,
   38,
   39,
   40),
  'cv_scores': array([0.8417445 , 0.84393137, 0.84113339, 0.84218943, 0.84486828]),
  'avg_score': 0.8427733960444744,
  'feature_names': ('Available Extra Rooms in Hospital',
   'staff_available',
   'Visitors with Patient',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_D',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Olivia',
   'doctor_name_Dr Sam',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Simon',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Age_91-100',
   'gender_Other',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Minor',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease',
   'health_conditions_High Blood Pressure',
   'health_conditions_Other',
   'Insurance_Yes'),
  'ci_bound': 0.0018011225528318932,
  'std_dev': 0.0014013345361560902,
  'std_err': 0.0007006672680780451},
 39: {'feature_idx': (0,
   1,
   2,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   10,
   11,
   12,
   13,
   15,
   16,
   17,
   18,
   19,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   29,
   31,
   32,
   33,
   34,
   35,
   36,
   37,
   38,
   39,
   40),
  'cv_scores': array([0.84174483, 0.84393285, 0.84112937, 0.84218622, 0.84485046]),
  'avg_score': 0.8427687463538682,
  'feature_names': ('Available Extra Rooms in Hospital',
   'staff_available',
   'Visitors with Patient',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_D',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr John',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Olivia',
   'doctor_name_Dr Sam',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Simon',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Age_91-100',
   'gender_Other',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Minor',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease',
   'health_conditions_High Blood Pressure',
   'health_conditions_Other',
   'Insurance_Yes'),
  'ci_bound': 0.0017960998677658592,
  'std_dev': 0.0013974267165375962,
  'std_err': 0.000698713358268798},
 40: {'feature_idx': (0,
   1,
   2,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   10,
   11,
   12,
   13,
   14,
   15,
   16,
   17,
   18,
   19,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   29,
   31,
   32,
   33,
   34,
   35,
   36,
   37,
   38,
   39,
   40),
  'cv_scores': array([0.84174483, 0.84393285, 0.84112937, 0.84218622, 0.84485046]),
  'avg_score': 0.8427687463538682,
  'feature_names': ('Available Extra Rooms in Hospital',
   'staff_available',
   'Visitors with Patient',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_D',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr John',
   'doctor_name_Dr Mark',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Olivia',
   'doctor_name_Dr Sam',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Simon',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Age_91-100',
   'gender_Other',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Minor',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease',
   'health_conditions_High Blood Pressure',
   'health_conditions_Other',
   'Insurance_Yes'),
  'ci_bound': 0.0017960998677658809,
  'std_dev': 0.001397426716537613,
  'std_err': 0.0006987133582688064},
 41: {'feature_idx': (0,
   1,
   2,
   3,
   4,
   5,
   6,
   7,
   8,
   9,
   10,
   11,
   12,
   13,
   14,
   15,
   16,
   17,
   18,
   19,
   20,
   21,
   22,
   23,
   24,
   25,
   26,
   27,
   28,
   29,
   30,
   31,
   32,
   33,
   34,
   35,
   36,
   37,
   38,
   39,
   40),
  'cv_scores': array([0.84174483, 0.84393285, 0.84112937, 0.84218622, 0.84485046]),
  'avg_score': 0.8427687463538682,
  'feature_names': ('Available Extra Rooms in Hospital',
   'staff_available',
   'Visitors with Patient',
   'Admission_Deposit',
   'Department_anesthesia',
   'Department_gynecology',
   'Department_radiotherapy',
   'Department_surgery',
   'Ward_Facility_Code_B',
   'Ward_Facility_Code_C',
   'Ward_Facility_Code_D',
   'Ward_Facility_Code_E',
   'Ward_Facility_Code_F',
   'doctor_name_Dr John',
   'doctor_name_Dr Mark',
   'doctor_name_Dr Nathan',
   'doctor_name_Dr Olivia',
   'doctor_name_Dr Sam',
   'doctor_name_Dr Sarah',
   'doctor_name_Dr Simon',
   'doctor_name_Dr Sophia',
   'Age_11-20',
   'Age_21-30',
   'Age_31-40',
   'Age_41-50',
   'Age_51-60',
   'Age_61-70',
   'Age_71-80',
   'Age_81-90',
   'Age_91-100',
   'gender_Male',
   'gender_Other',
   'Type of Admission_Trauma',
   'Type of Admission_Urgent',
   'Severity of Illness_Minor',
   'Severity of Illness_Moderate',
   'health_conditions_Diabetes',
   'health_conditions_Heart disease',
   'health_conditions_High Blood Pressure',
   'health_conditions_Other',
   'Insurance_Yes'),
  'ci_bound': 0.0017960998677653498,
  'std_dev': 0.0013974267165371996,
  'std_err': 0.0006987133582685998}}

reg = LinearRegression()

# Forward feature selection with 8 features
sfs = SFS(
    reg,
    k_features=8,
    forward=True,
    floating=False,
    scoring="r2",
    n_jobs=-1,
    verbose=2,
    cv=5,
)

# Perform SFFS
sfs = sfs.fit(x_train, y_train)

[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  37 tasks      | elapsed:   49.2s
[Parallel(n_jobs=-1)]: Done  41 out of  41 | elapsed:   52.9s finished

[2024-05-06 09:41:52] Features: 1/8 -- score: 0.49188988610314494[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  37 tasks      | elapsed:  1.1min
[Parallel(n_jobs=-1)]: Done  40 out of  40 | elapsed:  1.2min finished

[2024-05-06 09:43:04] Features: 2/8 -- score: 0.6046160397618378[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  39 out of  39 | elapsed:  1.1min finished

[2024-05-06 09:44:09] Features: 3/8 -- score: 0.6461909142668075[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  38 out of  38 | elapsed:  1.2min finished

[2024-05-06 09:45:21] Features: 4/8 -- score: 0.7013054914238064[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  37 out of  37 | elapsed:  1.2min finished

[2024-05-06 09:46:35] Features: 5/8 -- score: 0.7323069421611198[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  36 out of  36 | elapsed:  1.3min finished

[2024-05-06 09:47:56] Features: 6/8 -- score: 0.8191351388509401[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  35 out of  35 | elapsed:  1.4min finished

[2024-05-06 09:49:22] Features: 7/8 -- score: 0.8303282862064949[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  34 out of  34 | elapsed:  1.4min finished

[2024-05-06 09:50:46] Features: 8/8 -- score: 0.8395075505200165

# Selecting the features which are important for the model
feat_cols = list(sfs.k_feature_idx_)
print(feat_cols)

[4, 5, 6, 7, 21, 22, 23, 24]

# Checking the names of the important features
x_train.columns[feat_cols]

Index(['Department_anesthesia', 'Department_gynecology',
       'Department_radiotherapy', 'Department_surgery', 'Age_11-20',
       'Age_21-30', 'Age_31-40', 'Age_41-50'],
      dtype='object')

# Creating the new x_train data
x_train_final = x_train[x_train.columns[feat_cols]]

# Creating the new x_test data
x_test_final = x_test[x_train_final.columns]

# Fitting Linear Regression model on the new training data
lin_reg_model2 = LinearRegression()
lin_reg_model2.fit(x_train_final, y_train)

LinearRegression()

LinearRegression()

# Checking model performance on the training data
lin_reg_model2_train_perf = model_performance_regression(lin_reg_model2, x_train_final, y_train)
lin_reg_model2_train_perf

# Checking model performance on the testing data
lin_reg_model2_test_perf = model_performance_regression(lin_reg_model2, x_test_final, y_test)
lin_reg_model2_test_perf

# Training performance comparison

models_train_comp_df = pd.concat(
    [linear_reg.T, lin_reg_model2_train_perf.T], axis=1,
)

models_train_comp_df.columns = [
    "Linear Regression Scikit-learn",
    "Linear Regression Scikit-learn (SFS features)",
]

print("Training performance comparison:")
models_train_comp_df

Training performance comparison:

# Testing performance comparison

models_test_comp_df = pd.concat(
    [linear_reg_test.T, lin_reg_model2_test_perf.T], axis=1,
)

models_test_comp_df.columns = [
    "Linear Regression Scikit-learn",
    "Linear Regression Scikit-learn (SFS features)",
]

print("Test performance comparison:")
models_test_comp_df

Test performance comparison:

# Convert notebook to html
!jupyter nbconvert --to html "/content/drive/My Drive/Colab Notebooks/Copy of FDS_Project_LearnerNotebook_FullCode.ipynb"

	count	mean	std	min	25%	50%	75%	max
Available Extra Rooms in Hospital	500000.0	3.638800	2.698124	0.000000	2.000000	3.000000	4.000000	24.00000
staff_available	500000.0	5.020470	3.158103	0.000000	2.000000	5.000000	8.000000	10.00000
Visitors with Patient	500000.0	3.549414	2.241054	0.000000	2.000000	3.000000	4.000000	32.00000
Admission_Deposit	500000.0	4722.315734	1047.324220	1654.005148	4071.714532	4627.003792	5091.612717	10104.72639
Stay (in days)	500000.0	12.381062	7.913174	3.000000	8.000000	9.000000	11.000000	51.00000

Models	RMSE	MAE	R-squared	Adj. R-squared	MAPE
Least Squares	3.144055	2.155765	0.843028	0.842964	19.676966
Ridge Regression	3.144057	2.155826	0.843028	0.842963	19.677968
Ridge Regression Tuned	3.144055	2.155771	0.843028	0.842964	19.677066
Lasso Regression	6.064339	3.873332	0.416006	0.415766	34.652716
Lasso Regression Tuned	3.144315	2.157198	0.843002	0.842938	19.702959
Elastic Net Regression	6.556087	4.678504	0.317455	0.317175	40.121657
Elastic Net Regression Tuned	3.157478	2.178911	0.841685	0.841620	19.981572

	Linear Regression Scikit-learn	Linear Regression Scikit-learn (SFS features)
RMSE	3.135093	3.167762
MAE	2.146244	2.167470
R-squared	0.842813	0.839520
Adj. R-squared	0.842796	0.839516
MAPE	19.591833	19.769004

	Linear Regression Scikit-learn	Linear Regression Scikit-learn (SFS features)
RMSE	3.144055	3.175516
MAE	2.155765	2.174951
R-squared	0.843028	0.839871
Adj. R-squared	0.842964	0.839858
MAPE	19.676966	19.834250

Hospital Length of Stay (LOS) Prediction¶

Context:¶

Objective:¶

Data Dictionary:¶

Approach to solve the problem:¶

Importing Libraries¶

Data Overview¶

Exploratory Data Analysis (EDA)¶

Univariate Analysis¶

Length of stay¶

Admission Deposit¶

Visitors with Patients¶

Bivariate Analysis¶

Data Preparation for Model Building¶

Model Building¶

Linear Regression¶

Regularization¶

Ridge Regression¶

Ridge Regression with default parameters¶

Ridge Regression with optimized $\large\alpha$¶

Lasso Regression¶

Lasso Regression with default parameters¶

Lasso Regression with optimized $\large\alpha$¶

Elastic Net Regression¶

Elastic Net Regression with default parameters¶

Elastic Net Regression with optimized $\alpha$ and $L_1-ratio$¶

Forward Feature Selection using SequentialFeatureSelector¶

Next Steps¶

	Available Extra Rooms in Hospital	Department	Ward_Facility_Code	doctor_name	staff_available	patientid	Age	gender	Type of Admission	Severity of Illness	health_conditions	Visitors with Patient	Insurance	Admission_Deposit	Stay (in days)
0	4	gynecology	D	Dr Sophia	0	33070	41-50	Female	Trauma	Extreme	Diabetes	4	Yes	2966.408696	8
1	4	gynecology	B	Dr Sophia	2	34808	31-40	Female	Trauma	Minor	Heart disease	2	No	3554.835677	9
2	2	gynecology	B	Dr Sophia	8	44577	21-30	Female	Trauma	Extreme	Diabetes	2	Yes	5624.733654	7
3	4	gynecology	D	Dr Olivia	7	3695	31-40	Female	Urgent	Moderate	NaN	4	No	4814.149231	8
4	2	anesthesia	E	Dr Mark	10	108956	71-80	Male	Trauma	Moderate	Diabetes	2	No	5169.269637	34

	Available Extra Rooms in Hospital	Department	Ward_Facility_Code	doctor_name	staff_available	patientid	Age	gender	Type of Admission	Severity of Illness	health_conditions	Visitors with Patient	Insurance	Admission_Deposit	Stay (in days)
499995	4	gynecology	F	Dr Sarah	2	43001	11-20	Female	Trauma	Minor	High Blood Pressure	3	No	4105.795901	10
499996	13	gynecology	F	Dr Olivia	8	85601	31-40	Female	Emergency	Moderate	Other	2	No	4631.550257	11
499997	2	gynecology	B	Dr Sarah	3	22447	11-20	Female	Emergency	Moderate	High Blood Pressure	2	No	5456.930075	8
499998	2	radiotherapy	A	Dr John	1	29957	61-70	Female	Trauma	Extreme	Diabetes	2	No	4694.127772	23
499999	3	gynecology	F	Dr Sophia	3	45008	41-50	Female	Trauma	Moderate	Heart disease	4	Yes	4713.868519	10

	Department_Name	Patients_Treated
doctor_name
Dr Isaac	[surgery]	3359
Dr John	[TB & Chest disease, anesthesia, radiotherapy]	51263
Dr Mark	[anesthesia, TB & Chest disease]	44410
Dr Nathan	[gynecology]	70777
Dr Olivia	[gynecology]	98352
Dr Sam	[radiotherapy]	55711
Dr Sarah	[gynecology]	99596
Dr Simon	[surgery]	1779
Dr Sophia	[gynecology]	74753

	Available Extra Rooms in Hospital	staff_available	Visitors with Patient	Admission_Deposit	Stay (in days)	Department_anesthesia	Department_gynecology	Department_radiotherapy	Department_surgery	Ward_Facility_Code_B	Ward_Facility_Code_C	Ward_Facility_Code_D	Ward_Facility_Code_E	Ward_Facility_Code_F	doctor_name_Dr John	doctor_name_Dr Mark	doctor_name_Dr Nathan	doctor_name_Dr Olivia	doctor_name_Dr Sam	doctor_name_Dr Sarah	doctor_name_Dr Simon	doctor_name_Dr Sophia	Age_11-20	Age_21-30	Age_31-40	Age_41-50	Age_51-60	Age_61-70	Age_71-80	Age_81-90	Age_91-100	gender_Male	gender_Other	Type of Admission_Trauma	Type of Admission_Urgent	Severity of Illness_Minor	Severity of Illness_Moderate	health_conditions_Diabetes	health_conditions_Heart disease	health_conditions_High Blood Pressure	health_conditions_Other	Insurance_Yes
0	4	0	4	2966.408696	8	False	True	False	False	False	False	True	False	False	False	False	False	False	False	False	False	True	False	False	False	True	False	False	False	False	False	False	False	True	False	False	False	True	False	False	False	True
1	4	2	2	3554.835677	9	False	True	False	False	True	False	False	False	False	False	False	False	False	False	False	False	True	False	False	True	False	False	False	False	False	False	False	False	True	False	True	False	False	True	False	False	False
2	2	8	2	5624.733654	7	False	True	False	False	True	False	False	False	False	False	False	False	False	False	False	False	True	False	True	False	False	False	False	False	False	False	False	False	True	False	False	False	True	False	False	False	True
3	4	7	4	4814.149231	8	False	True	False	False	False	False	True	False	False	False	False	False	True	False	False	False	False	False	False	True	False	False	False	False	False	False	False	False	False	True	False	True	False	False	False	False	False
4	2	10	2	5169.269637	34	True	False	False	False	False	False	False	True	False	False	True	False	False	False	False	False	False	False	False	False	False	False	False	True	False	False	True	False	True	False	False	True	True	False	False	False	False
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
499995	4	2	3	4105.795901	10	False	True	False	False	False	False	False	False	True	False	False	False	False	False	True	False	False	True	False	False	False	False	False	False	False	False	False	False	True	False	True	False	False	False	True	False	False
499996	13	8	2	4631.550257	11	False	True	False	False	False	False	False	False	True	False	False	False	True	False	False	False	False	False	False	True	False	False	False	False	False	False	False	False	False	False	False	True	False	False	False	True	False
499997	2	3	2	5456.930075	8	False	True	False	False	True	False	False	False	False	False	False	False	False	False	True	False	False	True	False	False	False	False	False	False	False	False	False	False	False	False	False	True	False	False	True	False	False
499998	2	1	2	4694.127772	23	False	False	True	False	False	False	False	False	False	True	False	False	False	False	False	False	False	False	False	False	False	False	True	False	False	False	False	False	True	False	False	False	True	False	False	False	False
499999	3	3	4	4713.868519	10	False	True	False	False	False	False	False	False	True	False	False	False	False	False	False	False	True	False	False	False	True	False	False	False	False	False	False	False	True	False	False	True	False	True	False	False	True