Created
May 18, 2020 09:45
-
-
Save Alakhator/0f53b090a10dec7682397146ef402b4e to your computer and use it in GitHub Desktop.
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() | |
test['Age_Count'] = test['Age'].apply(lambda x:age_count_dict.get(x,0)) | |
train["Occupation_Count"] = train.groupby(['Occupation'])['Occupation'].transform('count') | |
occupation_count_dict = train.groupby(['Occupation']).size().to_dict() | |
test['Occupation_Count'] = test['Occupation'].apply(lambda x:occupation_count_dict.get(x,0)) | |
train["Product_Category_1_Count"] = train.groupby(['Product_Category_1'])['Product_Category_1'].transform('count') | |
pc1_count_dict = train.groupby(['Product_Category_1']).size().to_dict() | |
test['Product_Category_1_Count'] = test['Product_Category_1'].apply(lambda x:pc1_count_dict.get(x,0)) | |
train["Product_Category_2_Count"] = train.groupby(['Product_Category_2'])['Product_Category_2'].transform('count') | |
pc2_count_dict = train.groupby(['Product_Category_2']).size().to_dict() | |
test['Product_Category_2_Count'] = test['Product_Category_2'].apply(lambda x:pc2_count_dict.get(x,0)) | |
train["Product_Category_3_Count"] = train.groupby(['Product_Category_3'])['Product_Category_3'].transform('count') | |
pc3_count_dict = train.groupby(['Product_Category_3']).size().to_dict() | |
test['Product_Category_3_Count'] = test['Product_Category_3'].apply(lambda x:pc3_count_dict.get(x,0)) | |
train["User_ID_Count"] = train.groupby(['User_ID'])['User_ID'].transform('count') | |
userID_count_dict = train.groupby(['User_ID']).size().to_dict() | |
test['User_ID_Count'] = test['User_ID'].apply(lambda x:userID_count_dict.get(x,0)) | |
train["Product_ID_Count"] = train.groupby(['Product_ID'])['Product_ID'].transform('count') | |
productID_count_dict = train.groupby(['Product_ID']).size().to_dict() | |
test['Product_ID_Count'] = test['Product_ID'].apply(lambda x:productID_count_dict.get(x,0)) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment