aniruddha27

from sklearn.model_selection import train_test_split

X = df
y = target

# training and validation set
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.2,random_state=27)

aniruddha27

from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error

lr = LinearRegression()

lr.fit(X_train,y_train)

rmse = np.sqrt(mean_squared_error(y_test,lr.predict(X_test)))
print(rmse)

aniruddha27

from sklearn.linear_model import Ridge
from sklearn.metrics import mean_squared_error

# different alpha values
alphas = [0.01, 0.1, 0.3, 1, 3, 5, 10, 15, 20]

for a in alphas:

    lr = Ridge(alpha=a)
    

aniruddha27

model = Ridge(alpha=3)
model.fit(X_train,y_train)

aniruddha27

log_pred = model.predict(test)
actual_pred = np.exp(log_pred)

aniruddha27

data_dict = {'Id':test_id,'SalePrice':actual_pred}

submit = pd.DataFrame(data_dict)
submit.to_csv('submission.csv',index=False)

aniruddha27

import pandas as pd 
import numpy as np 
import matplotlib.pyplot as plt 
plt.style.use('ggplot')

aniruddha27

df = pd.read_csv('drive/My Drive/AV/train.csv') 
df.head()

aniruddha27

df.drop(['PassengerId','Ticket','Name'],inplace=True,axis=1)

aniruddha27

#a single index
table = pd.pivot_table(data=df,index=['Sex'])
table