second try

run.py

@@ -5,6 +5,10 @@ from sklearn.compose import TransformedTargetRegressor
 from sklearn.model_selection import GridSearchCV
 from sklearn.preprocessing import QuantileTransformer, StandardScaler
 
+import tensorflow.keras
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import Dense
+
 train = pd.read_csv("train/in.tsv", header=None, sep="\t")
 train_expected = pd.read_csv("train/expected.tsv", header=None, sep="\t")
 dev_0 = pd.read_csv("dev-0/in.tsv", header=None, sep="\t")
@@ -12,11 +16,11 @@ test_A = pd.read_csv("test-A/in.tsv", header=None, sep="\t")
 
 
 def preprocess_data(df_to_process, main_df=None):
-    final_df = pd.get_dummies(df_to_process, columns=[1, 2])
-    final_df.drop(columns=[0], inplace=True)
-    numeric = [3, 4]
-    sc = StandardScaler()
-    final_df[numeric] = sc.fit_transform(final_df[numeric])
+    final_df = pd.get_dummies(df_to_process, columns=[0, 1, 2, 3, 4])
+    # final_df.drop(columns=[0], inplace=True)
+    # numeric = [3]
+    # sc = StandardScaler()
+    # final_df[numeric] = sc.fit_transform(final_df[numeric])
 
     if type(main_df) == pd.DataFrame:
         final_columns = [
@@ -30,44 +34,74 @@ def preprocess_data(df_to_process, main_df=None):
 
     return final_df
 
-
+f_train = pd.concat([train, dev_0])
 train_df = preprocess_data(train)
-dev_df = preprocess_data(dev_0, train_df)
+# dev_df = preprocess_data(dev_0, train_df)
 test_A_df = preprocess_data(test_A, train_df)
 y = train_expected[0]
 
-param_grid = {
-    "n_estimators": [100, 80, 60, 55, 51, 45],
-    "max_depth": [7, 8],
-    "reg_lambda": [0.26, 0.25, 0.2],
-}
-
-grid = GridSearchCV(
-    xg.XGBRFRegressor(), param_grid, refit=True, verbose=3, n_jobs=-1
-)  #
-regr_trans = TransformedTargetRegressor(
-    regressor=grid, transformer=QuantileTransformer(output_distribution="normal")
+# Define model
+# model = Sequential()
+model = tensorflow.keras.models.Sequential(
+    [
+        tensorflow.keras.layers.Dense(
+            128, activation="relu", input_dim=97, kernel_regularizer="l2"
+        ),
+        tensorflow.keras.layers.Dropout(0.5),
+        tensorflow.keras.layers.Dense(128 // 2, activation="relu", kernel_regularizer="l2"),
+        tensorflow.keras.layers.Dense(128 // 4, activation="relu", kernel_regularizer="l2"),
+        tensorflow.keras.layers.Dense(128 // 8, activation="relu", kernel_regularizer="l2"),
+        tensorflow.keras.layers.Dense(32, activation="relu", kernel_regularizer="l2"),
+        tensorflow.keras.layers.Dense(1),
+    ]
 )
+# model.add(Dense(16, input_dim=97, activation= "relu"))
+# model.add(Dense(32, activation= "relu"))
+# model.add(Dense(64, activation= "relu"))
+# model.add(Dense(32, activation= "relu"))
+# model.add(Dense(1))
+#model.summary() #Print model Summary
 
-# fitting the model for grid search
-grid_result = regr_trans.fit(train_df, y)
-best_params = grid_result.regressor_.best_params_
+model.compile(loss= "mean_squared_error" , optimizer="adam", metrics=["mean_squared_error"])
+model.fit(train_df, y, epochs=20)
 
-# using best params to create and fit model
-best_model = xg.XGBRFRegressor(
-    max_depth=best_params["max_depth"],
-    n_estimators=best_params["n_estimators"],
-    reg_lambda=best_params["reg_lambda"],
-)
-regr_trans = TransformedTargetRegressor(
-    regressor=best_model, transformer=QuantileTransformer(output_distribution="normal")
-)
 
-regr_trans.fit(train_df, y)
-dev0_predicted = regr_trans.predict(dev_df)
-test_A_predicted = regr_trans.predict(test_A_df)
-dev0_predicted = np.round(dev0_predicted, decimals=1)
+# param_grid = {
+#     "n_estimators": [110, 100, 80, 60, 55, 51, 45, 35, 25],
+#     "max_depth": [5, 6, 7, 8, 9, 10, 11],
+#     "reg_lambda": [0.26, 0.25, 0.2, 0.15, 0.10],
+# }
+#
+# grid = GridSearchCV(
+#     xg.XGBRFRegressor(), param_grid, refit=True, verbose=3, n_jobs=-1
+# )  #
+# regr_trans = TransformedTargetRegressor(
+#     regressor=grid, transformer=QuantileTransformer(output_distribution="normal")
+# )
+#
+# # fitting the model for grid search
+# grid_result = regr_trans.fit(train_df, y)
+# best_params = grid_result.regressor_.best_params_
+#
+# # using best params to create and fit model
+# best_model = xg.XGBRFRegressor(
+#     max_depth=best_params["max_depth"],
+#     n_estimators=best_params["n_estimators"],
+#     reg_lambda=best_params["reg_lambda"],
+# )
+# regr_trans = TransformedTargetRegressor(
+#     regressor=best_model, transformer=QuantileTransformer(output_distribution="normal")
+# )
+
+# regr_trans.fit(train_df, y)
+# dev0_predicted = regr_trans.predict(dev_df)
+# test_A_predicted = regr_trans.predict(test_A_df)
+
+# dev0_predicted = model.predict(dev_df)
+test_A_predicted = model.predict(test_A_df)
+
+# dev0_predicted = np.round(dev0_predicted, decimals=1)
 test_A_predicted = np.round(test_A_predicted, decimals=1)
 
-pd.DataFrame(dev0_predicted).to_csv("dev-0/out.tsv", header=None, index=None)
+# pd.DataFrame(dev0_predicted).to_csv("dev-0/out.tsv", header=None, index=None)
 pd.DataFrame(test_A_predicted).to_csv("test-A/out.tsv", header=None, index=None)