Created
September 22, 2020 02:24
-
-
Save dfuller22/21e8cc14dbcbd55d22057994e486c8d7 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
def regressor_tester(reg_, X_tr, X_te, y_tr, y_te, verbose=False, display_res=False, keep_preds=False): | |
import pandas as pd | |
import numpy as np | |
from sklearn import metrics | |
## Check if multiple regressors to check | |
if isinstance(reg_, list): | |
## Container for multiple regressor results + counter | |
count = 0 | |
holder = [] | |
## Looping through each regressor | |
for r in reg_: | |
## Fit/predict on train/test data | |
y_hat_train, y_hat_test = fit_n_pred(r, X_tr, X_te, y_tr, show_reg=verbose) | |
## Store/get training data metrics | |
tr_mse = metrics.mean_squared_error(y_tr, y_hat_train) | |
tr_rmse = np.sqrt(metrics.mean_squared_error(y_tr, y_hat_train)) | |
tr_r2 = metrics.r2_score(y_tr, y_hat_train) | |
## Store/get testing data metrics | |
te_mse = metrics.mean_squared_error(y_te, y_hat_test) | |
te_rmse = np.sqrt(metrics.mean_squared_error(y_te, y_hat_test)) | |
te_r2 = metrics.r2_score(y_te, y_hat_test) | |
## Creating structure for df in list format | |
reg_res = [['Name', 'Tr_MSE', 'Tr_RMSE', 'Tr_R2', 'Te_MSE', 'Te_RMSE', 'Te_R2'], | |
[str(type(r)), tr_mse, tr_rmse, tr_r2, te_mse, te_rmse, te_r2]] | |
## Convert list into dataframe + append to holder | |
res_df_inner = pd.DataFrame(reg_res[1:], columns=reg_res[0]) | |
holder.append(res_df_inner) | |
count += 1 | |
## Display counter + merge dfs into one | |
print(('---'*10), f'{count} regressors evaluated.', ('---'*10)) | |
res_df = pd.concat(holder, ignore_index=True) | |
## Optional Q.C. | |
if display_res: | |
display(res_df) | |
## Optional return of preds | |
if keep_preds: | |
return res_df, y_hat_train, y_hat_test | |
return res_df | |
else: | |
## Fit/predict on train/test data | |
y_hat_train, y_hat_test = fit_n_pred(reg_, X_tr, X_te, y_tr, show_reg=verbose) | |
## Store/get training data metrics | |
tr_mse = metrics.mean_squared_error(y_tr, y_hat_train) | |
tr_rmse = np.sqrt(metrics.mean_squared_error(y_tr, y_hat_train)) | |
tr_r2 = metrics.r2_score(y_tr, y_hat_train) | |
## Store/get testing data metrics | |
te_mse = metrics.mean_squared_error(y_te, y_hat_test) | |
te_rmse = np.sqrt(metrics.mean_squared_error(y_te, y_hat_test)) | |
te_r2 = metrics.r2_score(y_te, y_hat_test) | |
## Creating structure for df in list format | |
reg_res = [['Name', 'Tr_MSE', 'Tr_RMSE', 'Tr_R2', 'Te_MSE', 'Te_RMSE', 'Te_R2'], | |
[str(type(reg_)), tr_mse, tr_rmse, tr_r2, te_mse, te_rmse, te_r2]] | |
## Convert list into dataframe | |
res_df_ = pd.DataFrame(reg_res[1:], columns=reg_res[0]) | |
## Optional Q.C. | |
if display_res: | |
display(res_df_) | |
## Optional return of preds | |
if keep_preds: | |
return res_df_, y_hat_train, y_hat_test | |
return res_df_ | |
## NECESSARY CODE FOR PREDICTION ## | |
def fit_n_pred(reg_, X_tr, X_te, y_tr, show_reg=True): | |
## Try/Except if timer object available | |
try: | |
timer = Timer() | |
timer.start(disp_time=False) | |
except: | |
print('No timer for fitting.') | |
## Fit model to training data | |
reg_.fit(X_tr, y_tr) | |
## Get training/test predictions | |
y_hat_trn = reg_.predict(X_tr) | |
y_hat_tes = reg_.predict(X_te) | |
## Try/Except if timer available | |
try: | |
timer.stop(disp_time=False) | |
except: | |
pass | |
## Optional Q.C. | |
if show_reg: | |
display(reg_) | |
return y_hat_trn, y_hat_tes |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment