model_building.py

# -*- coding: utf-8 -*-
"""
Created on Mon Nov  9 16:23:01 2020

@author: brahmkeshwar
"""
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np

df = pd.read_csv('C:/Users/brahmkeshwar/ds_proj/eda_data.csv')

df.columns

df_model = df[['avg_salary','Rating','Size','Type of ownership','Industry','Sector','Revenue','num_comp','hourly','employer_provided','job_state','same_state','age','python_yn','spark','aws','excel','job_simp','desc_len','seniority']]

df_dum = pd.get_dummies(df_model)


from sklearn.model_selection import train_test_split
X = df_dum.drop('avg_salary',axis=1)
y = df_dum.avg_salary.values
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

import statsmodels.api as sm

X_sm = X =sm.add_constant(X)
model = sm.OLS(y,X_sm)
model.fit().summary()

from sklearn.linear_model import LinearRegression , Lasso
from sklearn.model_selection import cross_val_score

lm = LinearRegression()
lm.fit(X_train,y_train)

np.mean(cross_val_score(lm,X_train,y_train,scoring='neg_mean_absolute_error',cv=3))

lm_l=Lasso()
lm_l.fit(X_train,y_train)

np.mean(cross_val_score(lm_l,X_train,y_train,scoring='neg_mean_absolute_error',cv=3))

alpha = []
error = []

for i in range(1,100):
    alpha.append(i/100)
    lm_l = Lasso(alpha=i/100)
    lm_l.fit(X_train,y_train)
    error.append(np.mean(cross_val_score(lm_l,X_train,y_train,scoring='neg_mean_absolute_error',cv=3)))
    
plt.plot(alpha,error)

err = tuple(zip(alpha,error))
df_err = pd.DataFrame(err,columns=['alpha','error'])
df_err[df_err.error==max(df_err.error)]

from sklearn.ensemble import RandomForestRegressor
rf=RandomForestRegressor()

np.mean(cross_val_score(rf,X_train,y_train,scoring='neg_mean_absolute_error',cv=3))

from sklearn.model_selection import GridSearchCV

parameters = {'n_estimators':range(10,300,10), 'criterion':('mse','mae'), 'max_features':('auto','sqrt','log2')}

gs = GridSearchCV(rf,parameters,scoring='neg_mean_absolute_error',cv=3)
gs.fit(X_train,y_train)

gs.best_score_
gs.best_estimator_

pred_lm = lm.predict(X_test)
pred_lm_l = lm_l.predict(X_test)
pred_rf = gs.best_estimator_.predict(X_test)

from sklearn.metrics import mean_absolute_error

mean_absolute_error( y_test, pred_lm)
mean_absolute_error( y_test, pred_lm_l)
mean_absolute_error( y_test, pred_rf)

mean_absolute_error( y_test, (pred_rf+pred_lm)/2)