operations.py

#importing required classes
from sklearn.model_selection import StratifiedShuffleSplit
from sklearn.preprocessing import StandardScaler,OneHotEncoder
from sklearn.impute import SimpleImputer
from sklearn.pipeline import Pipeline
from sklearn.compose import ColumnTransformer
from sklearn.linear_model import LinearRegression
from sklearn.tree import DecisionTreeRegressor
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import root_mean_squared_error
from sklearn.model_selection import cross_val_score


#loading dataset
import pandas as pd
import numpy as np


housing=pd.read_csv("housing.csv")

#stratified_test set

housing["income_cat"]=pd.cut(housing["median_income"],
                             bins=[0.0,1.5,3.0,4.5,6.0,np.inf]
                             ,labels=[1,2,3,4,5])

split=StratifiedShuffleSplit(n_splits=1,test_size=0.2,random_state=42)
for train_index,test_index in split.split(housing,housing['income_cat']):
    strat_train_set=housing.loc[train_index].drop("income_cat",axis=1)
    strat_test_set=housing.loc[test_index].drop("income_cat",axis=1)

#working on training set
housing=strat_train_set.copy()
housing_labels=housing['median_house_value'].copy()
housing=housing.drop('median_house_value',axis=1)
#print(housing,housing_labels)

#separating numerical and categorical values
num_attribs=housing.drop("ocean_proximity",axis=1).columns.tolist()
cat_attribs=["ocean_proximity"]

#pipelines
num_pipeline= Pipeline([
    ("imputer",SimpleImputer(strategy="median")),
    ("scaler",StandardScaler())
])

cat_pipeline= Pipeline([
    ("encoder",OneHotEncoder(handle_unknown="ignore"))
])

full_pipeline=ColumnTransformer([
    ("nums",num_pipeline,num_attribs),
    ("cats",cat_pipeline,cat_attribs)
])

#transform data
housing_prep=full_pipeline.fit_transform(housing)
#print(housing_prep)

#training models

#linearRegression
lin_reg=LinearRegression()
lin_reg.fit(housing_prep,housing_labels)
linpred=lin_reg.predict(housing_prep)
#lin_rmse=root_mean_squared_error(housing_labels,linpred)
#print(f"the root mean squared error for lim-reg is{lin_rmse}\n")
lin_rmse= -cross_val_score(lin_reg,housing_prep,housing_labels,scoring="neg_root_mean_squared_error",cv=10)
print("for linear regression ")
print(pd.Series(lin_rmse).describe())

#descision tree
dec_reg=DecisionTreeRegressor()
dec_reg.fit(housing_prep,housing_labels)
decpred=dec_reg.predict(housing_prep)
#dec_rmse=root_mean_squared_error(housing_labels,decpred)
#print(f"the root mean squared error for dec-reg is{dec_rmse}\n")
dec_rmse= -cross_val_score(dec_reg,housing_prep,housing_labels,scoring="neg_root_mean_squared_error",cv=10)
print("for descision tree regression ")
print(pd.Series(dec_rmse).describe())


#randomforest
ran_reg=RandomForestRegressor()
ran_reg.fit(housing_prep,housing_labels)
ranpred=ran_reg.predict(housing_prep)
#ran_rmse=root_mean_squared_error(housing_labels,ranpred)
#print(f"the root mean squared error for ran-reg is{ran_rmse}\n")
ran_rmse= -cross_val_score(ran_reg,housing_prep,housing_labels,scoring="neg_root_mean_squared_error",cv=10)
print("for random forest ")
print(pd.Series(ran_rmse).describe())