Code_CalvingFeatureSelection

import pandas as pd
import numpy as np
from sklearn.feature_selection import SelectKBest, f_classif
from sklearn.impute import SimpleImputer
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import OneHotEncoder

# ------------------------------------- Filter Method -----------------------------------------------------

# Load your dataset into a pandas DataFrame
df = pd.read_csv('hour.csv')

# Separate the features (X) and target variable (y)
y = df['hoursbefore']
X = df[["parity", "TIME", "avgtotalmotion", "avgtotalsteps", "avglyingbouts", "avgrumination", "avgactivity", "avghoursstanding", "avghourslying"]]

# Identify numeric and categorical columns
numeric_cols = X.select_dtypes(include=np.number).columns
categorical_cols = X.select_dtypes(include='object').columns

# Create transformers for numeric and categorical columns
numeric_transformer = SimpleImputer(strategy='mean')
categorical_transformer = SimpleImputer(strategy='most_frequent')

# Apply transformers to the columns
preprocessor = ColumnTransformer(
    transformers=[
        ('numeric', numeric_transformer, numeric_cols),
        ('categorical', categorical_transformer, categorical_cols)
    ])

# Fit and transform the data
X_preprocessed = preprocessor.fit_transform(X)

# Convert back to DataFrame
X_preprocessed = pd.DataFrame(X_preprocessed, columns=numeric_cols.tolist() + categorical_cols.tolist())

# Perform one-hot encoding
encoder = OneHotEncoder(drop='first')
X_encoded = encoder.fit_transform(X_preprocessed[categorical_cols])
X_encoded = pd.DataFrame(X_encoded.toarray(), columns=encoder.get_feature_names_out(categorical_cols))

# Concatenate encoded features with numeric features
X_final = pd.concat([X_preprocessed[numeric_cols], X_encoded], axis=1)

# Initialize SelectKBest with f_classif scoring function
k = 5  # Number of top features to select
selector = SelectKBest(score_func=f_classif, k=k)

# Fit the selector to the data and transform the features
X_new = selector.fit_transform(X_final, y)

# Get the selected feature indices
feature_indices = selector.get_support(indices=True)

# Get the selected feature names
selected_features = X_final.columns[feature_indices]

# Print the selected feature names
print("Selected Features:")
print(selected_features)

# Check the size of the new feature set
print("Size of New Feature Set:", X_new.shape)


# ------------------------------------- Wrapper Method -----------------------------------------------------

# Separate the features (X) and target variable (y)
y = df['target_variable']
X = df.drop('target_variable', axis=1)

# Initialize the Random Forest classifier
clf = RandomForestClassifier()

# Initialize RFE with the classifier and number of desired features to select
n_features = 200  # Number of top features to select
rfe = RFE(estimator=clf, n_features_to_select=n_features)

# Fit RFE to the data and transform the features
X_new = rfe.fit_transform(X, y)

# Get the selected feature indices
feature_indices = rfe.get_support(indices=True)

# Print the selected feature indices
print("Selected Feature Indices:")
print(feature_indices)

# Check the size of the new feature set
print("Size of New Feature Set:", X_new.shape)


# ------------------------------------- Embedded Method -----------------------------------------------------

# Separate the features (X) and target variable (y)
y = df['target_variable']
X = df.drop('target_variable', axis=1)

# Initialize the RandomForestClassifier model
rf_model = RandomForestClassifier(random_state=45)

# Fit the RandomForestClassifier model to the data
rf_model.fit(X, y)

# Get feature importances from the trained model
feature_importances = rf_model.feature_importances_

# Sort the feature importances in descending order
sorted_indices = feature_importances.argsort()[::-1]

# Set the number of top features to select
k = 5

# Get the indices of the top k features
selected_feature_indices = sorted_indices[:k]

# Get the selected feature names
selected_features = X.columns[selected_feature_indices]

# Print the selected feature names
print("Selected Features:")
print(selected_features)

# Create a new DataFrame with the selected features
X_new = X[selected_features]

# Check the size of the new feature set
print("Size of New Feature Set:", X_new.shape)