View fe13.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
print(train['Gender'].unique()) | |
print(train['City_Category'].unique()) | |
print(train['Age'].unique()) | |
print(train['Stay_In_Current_City_Years'].unique()) | |
print(train['Product_ID'].unique()) |
View fe12.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
train['Gender'].unique() |
View fe11.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
train.info() |
View fe10.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
train["Product_Cat1_MaxPrice"] = train.groupby(['Product_Category_1'])['Purchase'].transform('max') | |
pc1_max_dict = train.groupby(['Product_Category_1'])['Purchase'].max().to_dict() | |
test['Product_Cat1_MaxPrice'] = test['Product_Category_1'].apply(lambda x:pc1_max_dict.get(x,0)) | |
train["Product_Cat1_MeanPrice"] = train.groupby(['Product_Category_1'])['Purchase'].transform('mean') | |
pc1_mean_dict = train.groupby(['Product_Category_1'])['Purchase'].mean().to_dict() | |
test['Product_Cat1_MeanPrice'] = test['Product_Category_1'].apply(lambda x:pc1_mean_dict.get(x,0)) | |
train["Age_Count"] = train.groupby(['Age'])['Age'].transform('count') | |
age_count_dict = train.groupby(['Age']).size().to_dict() |
View fe9.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
train["User_ID_MinPrice"] = train.groupby(['User_ID'])['Purchase'].transform('min') | |
userID_min_dict = train.groupby(['User_ID'])['Purchase'].min().to_dict() | |
test['User_ID_MinPrice'] = test['User_ID'].apply(lambda x:userID_min_dict.get(x,0)) | |
train["User_ID_MaxPrice"] = train.groupby(['User_ID'])['Purchase'].transform('max') | |
userID_max_dict = train.groupby(['User_ID'])['Purchase'].max().to_dict() | |
test['User_ID_MaxPrice'] = test['User_ID'].apply(lambda x:userID_max_dict.get(x,0)) | |
train["Product_ID_MinPrice"] = train.groupby(['Product_ID'])['Purchase'].transform('min') | |
productID_min_dict = train.groupby(['Product_ID'])['Purchase'].min().to_dict() |
View fe8.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
train["User_ID_MeanPrice"] = train.groupby(['User_ID'])['Purchase'].transform('mean') | |
userID_mean_dict = train.groupby(['User_ID'])['Purchase'].mean().to_dict() | |
test['User_ID_MeanPrice'] = test['User_ID'].apply(lambda x:userID_mean_dict.get(x,0)) | |
train["Product_ID_MeanPrice"] = train.groupby(['Product_ID'])['Purchase'].transform('mean') | |
productID_mean_dict = train.groupby(['Product_ID'])['Purchase'].mean().to_dict() | |
test['Product_ID_MeanPrice'] = test['Product_ID'].apply(lambda x:productID_mean_dict.get(x,0)) |
View fe7.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
dtr = DecisionTreeRegressor() | |
dtr.fit(X_train,Y_train) | |
y_pred = dtr.predict(X_test) | |
y_pred_dt=dtr.predict(test) | |
submission['Purchase'] = y_pred_dt | |
submission.to_csv('dtr_model3.csv',index=False) | |
mse = mean_squared_error(Y_test, y_pred) | |
print("RMSE Error:", np.sqrt(mse)) | |
r2 = r2_score(Y_test, y_pred) | |
print("R2 Score:", r2) |
View fe6.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
train.fillna(-999, inplace=True) | |
test.fillna(-999, inplace=True) |
View fe5.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
gender_dict = {'F':0, 'M':1} | |
age_dict = {'0-17':0, '18-25':1, '26-35':2, '36-45':3, '46-50':4, '51-55':5, '55+':6} | |
city_dict = {'A':0, 'B':1, 'C':2} | |
stay_dict = {'0':0, '1':1, '2':2, '3':3, '4+':4} | |
train["Gender"] = train["Gender"].apply(lambda x: gender_dict[x]) | |
test["Gender"] = test["Gender"].apply(lambda x: gender_dict[x]) | |
train["Age"] = train["Age"].apply(lambda x: age_dict[x]) | |
test["Age"] = test["Age"].apply(lambda x: age_dict[x]) |
View fe4.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
submission = pd.DataFrame() | |
submission['User_ID'] = test['User_ID'] | |
submission['Product_ID'] = test['Product_ID'] |
NewerOlder