import pandas as pd

bank_df = pd.read_csv("train.csv", index_col="id")
bank_df = bank_df.drop(['CustomerId', 'Surname'], axis=1)
bank_df = bank_df.sample(frac=1)
bank_df.head()

from sklearn.impute import SimpleImputer
from sklearn.preprocessing import OrdinalEncoder, MinMaxScaler

cat_col = [1,2]
num_col = [0,3,4,5,6,7,8,9]

# Filling missing categorical values
cat_impute = SimpleImputer(strategy="most_frequent")
bank_df.iloc[:,cat_col] = cat_impute.fit_transform(bank_df.iloc[:,cat_col])

# Filling missing numerical values
num_impute = SimpleImputer(strategy="median")
bank_df.iloc[:,num_col] = num_impute.fit_transform(bank_df.iloc[:,num_col])


# Encode categorical features as an integer array.
cat_encode = OrdinalEncoder()
bank_df.iloc[:,cat_col] = cat_encode.fit_transform(bank_df.iloc[:,cat_col])


# Scaling numerical values.
scaler = MinMaxScaler()
bank_df.iloc[:,num_col] = scaler.fit_transform(bank_df.iloc[:,num_col])

bank_df.head()

from sklearn.impute import SimpleImputer
from sklearn.preprocessing import OrdinalEncoder, MinMaxScaler
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline


# Identify numerical and categorical columns
cat_col = [1,2]
num_col = [0,3,4,5,6,7,8,9]

# Transformers for numerical data
numerical_transformer = Pipeline(steps=[
    ('imputer', SimpleImputer(strategy='mean')),
    ('scaler', MinMaxScaler())
])

# Transformers for categorical data
categorical_transformer = Pipeline(steps=[
    ('imputer', SimpleImputer(strategy='most_frequent')),
    ('encoder', OrdinalEncoder())
])

# Combine transformers into a ColumnTransformer
preproc_pipe = ColumnTransformer(
    transformers=[
        ('num', numerical_transformer, num_col),
        ('cat', categorical_transformer, cat_col)
    ],
    remainder="passthrough"
)

# Apply the preprocessing pipeline
bank_df = preproc_pipe.fit_transform(bank_df)
bank_df[0]

array([0.712     , 0.24324324, 0.6       , 0.        , 0.33333333,
       1.        , 1.        , 0.76443485, 2.        , 0.        ,
       0.        ])

preproc_pipe

from sklearn.model_selection import train_test_split

X = bank_df.drop("Exited", axis=1).values
y = bank_df.Exited.values

X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.3, random_state=125
)

from sklearn.feature_selection import SelectKBest, chi2
from sklearn.ensemble import RandomForestClassifier

KBest = SelectKBest(chi2, k="all")
X_train = KBest.fit_transform(X_train, y_train)
X_test = KBest.transform(X_test)

model = RandomForestClassifier(n_estimators=100, random_state=125)

model.fit(X_train,y_train)

model.score(X_test, y_test)

0.8613035487063481

KBest = SelectKBest(chi2, k="all")
model = RandomForestClassifier(n_estimators=100, random_state=125)

train_pipe = Pipeline(
    steps=[
        ("KBest", KBest),
        ("RFmodel", model),
    ]
)

train_pipe.fit(X_train,y_train)

train_pipe.score(X_test, y_test)

0.8613035487063481

train_pipe

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import OrdinalEncoder, MinMaxScaler
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.feature_selection import SelectKBest, chi2
from sklearn.ensemble import RandomForestClassifier

#loading the data
bank_df = pd.read_csv("train.csv", index_col="id")
bank_df = bank_df.drop(['CustomerId', 'Surname'], axis=1)
bank_df = bank_df.sample(frac=1)


# Splitting data into training and testing sets
X = bank_df.drop(["Exited"],axis=1)
y = bank_df.Exited

X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.3, random_state=125
)

# Identify numerical and categorical columns
cat_col = [1,2]
num_col = [0,3,4,5,6,7,8,9]

# Transformers for numerical data
numerical_transformer = Pipeline(steps=[
    ('imputer', SimpleImputer(strategy='mean')),
    ('scaler', MinMaxScaler())
])

# Transformers for categorical data
categorical_transformer = Pipeline(steps=[
    ('imputer', SimpleImputer(strategy='most_frequent')),
    ('encoder', OrdinalEncoder())
])

# Combine pipelines using ColumnTransformer
preproc_pipe = ColumnTransformer(
    transformers=[
        ('num', numerical_transformer, num_col),
        ('cat', categorical_transformer, cat_col)
    ],
    remainder="passthrough"
)

# Selecting the best features
KBest = SelectKBest(chi2, k="all")

# Random Forest Classifier
model = RandomForestClassifier(n_estimators=100, random_state=125)

# KBest and model pipeline
train_pipe = Pipeline(
    steps=[
        ("KBest", KBest),
        ("RFmodel", model),
    ]
)

# Combining the preprocessing and training pipelines
complete_pipe = Pipeline(
    steps=[
       
        ("preprocessor", preproc_pipe),
        ("train", train_pipe),
    ]
)

# running the complete pipeline
complete_pipe.fit(X_train,y_train)

# model accuracy
complete_pipe.score(X_test, y_test)

0.8592837955201874

complete_pipe

import skops.io as sio

sio.dump(complete_pipe, "bank_pipeline.skops")

new_pipe = sio.load("bank_pipeline.skops", trusted=True)
new_pipe

from sklearn.metrics import accuracy_score, f1_score

predictions = new_pipe.predict(X_test)
accuracy = accuracy_score(y_test, predictions)
f1 = f1_score(y_test, predictions, average="macro")

print("Accuracy:", str(round(accuracy, 2) * 100) + "%", "F1:", round(f1, 2))

Accuracy: 86.0% F1: 0.76