Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
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
@start_new_thread | |
def send_mail_final(target_variable,df_train,df_test,email_id,message,date_column=None): | |
try: | |
df_pred=auto_predictor(Target_Variable=target_variable,data_raw=df_train,n_valid=int(0.1*len(df_train)),data_to_predict=df_test,date_column=date_column) | |
df_pred=pd.DataFrame(df_pred) | |
df_pred.to_csv('predictions.csv') | |
recepient = email_id | |
email=EmailMessage('Processed Data',message,EMAIL_HOST_USER,[recepient]) | |
email.attach_file('predictions.csv') |
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
def auto_predictor(Target_Variable,data_raw,n_valid,data_to_predict,date_column=None): | |
if date_column: | |
data_raw['{}'.format(date_column)]= pd.to_datetime(data_raw['{}'.format(date_column)]) | |
data_to_predict['{}'.format(date_column)]= pd.to_datetime(data_to_predict['{}'.format(date_column)]) | |
intermed=data_trainer(Target_Variable=Target_Variable,data_raw=data_raw,n_valid=n_valid,date_column=date_column) | |
return(auto_applyer(leaf_value=intermed[0],feature_value=intermed[1],feature_list=intermed[2],df_raw1=data_raw,df_test=data_to_predict,target_column=Target_Variable,date_column=date_column)) | |
else: | |
intermed=data_trainer(Target_Variable=Target_Variable,data_raw=data_raw,n_valid=n_valid) | |
return(auto_applyer(leaf_value=intermed[0],feature_value=intermed[1],feature_list=intermed[2],df_raw1=data_raw,df_test=data_to_predict,target_column=Target_Variable)) |
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
def auto_applyer(leaf_value,feature_value,feature_list,df_raw1,df_test,target_column,date_column=None): | |
reset_rf_samples() | |
if date_column: | |
if date_column in df_test: | |
add_datepart(df_test,date_column) | |
if date_column in df_raw1: | |
add_datepart(df_raw1,date_column) | |
'''First we will pre process both test and raw data''' | |
train_cats(df_raw1) |
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
''' from here we are doing the feature engineering''' | |
print(min_leaf_a) | |
reset_rf_samples() | |
z=RandomForestRegressor(n_jobs=-1,min_samples_leaf= min_leaf_a,max_features= max_feature_a,oob_score=False,n_estimators=40) | |
z.fit(X_train,y_train) | |
fi=rf_feat_importance(z,df) | |
score=0 | |
final_feature_importance_value=0 | |
feature_importance_value_list=[0,0.001,0.002,0.0025,0.003,0.0035] | |
for feature_importance_value in feature_importance_value_list: |
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
def data_trainer(Target_Variable,data_raw,n_valid,date_column=None): | |
df_raw=data_raw | |
reset_rf_samples() | |
''' This if statement is to reduce the date part''' | |
if date_column: | |
add_datepart(df_raw,date_column) | |
train_cats(df_raw) | |
df,y,nas=proc_df(df_raw,Target_Variable) | |
n_trn=len(df)-n_valid |
NewerOlder