Created
August 18, 2020 13:57
-
-
Save shaan-shah/764ef256c48ab8c63cc05291c8402938 to your computer and use it in GitHub Desktop.
This gist was made to demonstrate code on medium.
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) | |
apply_cats(df=df_test,trn=df_raw1) | |
X,y,nas=proc_df(df_raw1,target_column) | |
X_test,_,nas = proc_df(df_test, na_dict=nas) | |
X=X[feature_list] | |
X_test=X_test[feature_list] | |
z=RandomForestRegressor(n_jobs=-1,min_samples_leaf=leaf_value,max_features=feature_value,oob_score=False,n_estimators=75) | |
z.fit(X,y) | |
fi = rf_feat_importance(z,X) | |
graphed=fi.plot('cols', 'imp', 'barh', figsize=(12,7), legend=False) | |
fig_save = graphed.get_figure() | |
fig_save.savefig('Feature Importance.png') | |
print(z.predict(X_test)) | |
return z.predict(X_test) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment