#import libraries
import pandas as pd
import numpy as np
import joblib
import warnings
warnings.filterwarnings('ignore')
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_squared_error, r2_score
#importing the dataset
df= pd.read_csv('clean_water_requirement_data.csv')
print(df.shape)

#finding the categorical and numerical columns
categorical_columns = df.select_dtypes(include=['object', 'category']).columns
numerical_columns = df.select_dtypes(include=['float64', 'int64']).columns

#encoding the categorical variables
from sklearn.preprocessing import LabelEncoder
label_encoder = LabelEncoder()
for col in categorical_columns:
    df[col] = label_encoder.fit_transform(df[col])

#separating input and target features in dataset
X = df.drop(columns=['water_requirement']) 
y=df.iloc[:,-1]

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

from sklearn.preprocessing import StandardScaler

# Apply StandardScaler
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

# Initialize the model with the provided best parameters
model = RandomForestRegressor(max_depth=20, n_estimators=200, random_state=42)

# Fit the model
model.fit(X_train, y_train)

# Predictions
y_pred = model.predict(X_test)

# Calculate performance metrics
mse = mean_squared_error(y_test, y_pred)
mae = mean_absolute_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)

# Save the model as a .pkl file using joblib
model_filename = 'random_forest_regressor_model.pkl'
joblib.dump(model, model_filename)