Sat, 16 Oct 2021 20:57:38 GMT

train_model.py

@@ -1,5 +1,3 @@
-# 要添加一个新单元，输入 '# %%'
-# 要添加一个新的标记单元，输入 '# %% [markdown]'
 # %%
 import pandas as pd
 
@@ -41,8 +39,8 @@ y = df[target_cols]
 data_keys = ['X_train', 'X_test', 'y_train', 'y_test']
 data_vals = train_test_split(X, y, test_size=0.2)
 train_test_data = dict(zip(data_keys, data_vals))
-train_test_data['X_test'] = test_set[feature_cols]
-train_test_data['y_test'] = test_set[target_cols]
+# train_test_data['X_test'] = test_set[feature_cols]
+# train_test_data['y_test'] = test_set[target_cols]
 # train_test_data = {
 #     'X_train': train_set[feature_cols],
 #     'y_train': train_set[target_cols],
@@ -79,17 +77,24 @@ for reg in [CatBoostRegressor, LGBMRegressor, XGBRegressor]:
 
 # %%
 from sklearn import metrics
-with open("cat.pickle", "rb") as f:
-    models = pickle.load(f)
-X, ys = train_test_data['X_test'], train_test_data['y_test']
-evals = []
-for target_col, reg in models.items():
-    y_hat = reg.predict(X)  # fake
-    y = ys[target_col]  # real
-    rmse = metrics.mean_squared_error(y, y_hat, squared=False)
-    r2 = metrics.r2_score(y, y_hat)
-    eval_dict = {'Error': target_col, 'RMSE': rmse, 'R^2': r2}
-    evals.append(eval_dict)
-pd.DataFrame(evals)
 
+
+def eval_model(regType):
+    with open(f"models/model_{regType.__name__}.pickle", "rb") as f:
+        models = pickle.load(f)
+    X, ys = train_test_data['X_test'], train_test_data['y_test']
+    evals = []
+    for target_col, reg in models.items():
+        y_hat = reg.predict(X)  # fake
+        y = ys[target_col]  # real
+        rmse = metrics.mean_squared_error(y, y_hat, squared=False)
+        r2 = metrics.r2_score(y, y_hat)
+        eval_dict = {'Error': target_col, 'RMSE': rmse, 'R^2': r2}
+        evals.append(eval_dict)
+    print(regType.__name__)
+    print(pd.DataFrame(evals))
+
+
+for reg in [CatBoostRegressor, LGBMRegressor, XGBRegressor]:
+    eval_model(reg)
 # %%