xx

run.py

@@ -3,7 +3,11 @@ import pandas as pd
 import xgboost as xg
 from sklearn.compose import TransformedTargetRegressor
 from sklearn.model_selection import GridSearchCV
-from sklearn.preprocessing import QuantileTransformer, StandardScaler
+from sklearn.preprocessing import (
+    QuantileTransformer,
+    StandardScaler,
+    PolynomialFeatures,
+)
 
 import tensorflow.keras
 from tensorflow.keras.models import Sequential
@@ -15,14 +19,12 @@ dev_expected = pd.read_csv("dev-0/expected.tsv", header=None, sep="\t")
 dev_0 = pd.read_csv("dev-0/in.tsv", header=None, sep="\t")
 test_A = pd.read_csv("test-A/in.tsv", header=None, sep="\t")
 
+poly = PolynomialFeatures(2, interaction_only=True)
+
 
 def preprocess_data(df_to_process, main_df=None):
-    final_df = pd.get_dummies(df_to_process, columns=[1, 3, 4])
-    final_df.drop(columns=[0], inplace=True)
-    final_df.drop(columns=[2], inplace=True)
-    # numeric = [3]
-    # sc = StandardScaler()
-    # final_df[numeric] = sc.fit_transform(final_df[numeric])
+    final_df = pd.get_dummies(df_to_process, columns=[0, 3, 4])
+    final_df.drop(columns=[1, 2], inplace=True)
 
     if type(main_df) == pd.DataFrame:
         final_columns = [
@@ -36,12 +38,13 @@ def preprocess_data(df_to_process, main_df=None):
 
     return final_df
 
-f_train = pd.concat([train, dev_0])
-f_train = preprocess_data(f_train)
-# dev_df = preprocess_data(dev_0, train_df)
-test_A_df = preprocess_data(test_A, f_train)
-y_expected = pd.concat([train_expected, dev_expected])
-y = y_expected[0]
+
+# f_train = pd.concat([train, dev_0])
+x_train = preprocess_data(train)
+dev_train = preprocess_data(dev_0, x_train)
+
+test_A_df = preprocess_data(test_A, x_train)
+y = train_expected[0]
 
 # Define model
 # model = Sequential()
@@ -51,27 +54,44 @@ y = y_expected[0]
 # Compile model
 # model.compile(loss='mean_squared_error', optimizer='adam')
 # evaluate model with stand
-model = tensorflow.keras.models.Sequential(
+model = Sequential(
     [
-        tensorflow.keras.layers.Dense(
-            128, activation="relu", input_dim=73,
-        ),
-        tensorflow.keras.layers.Dense(128 // 2, activation="relu"),
-        tensorflow.keras.layers.Dense(128 // 4, activation="relu"),
-        tensorflow.keras.layers.Dense(128 // 8, activation="relu"),
-        tensorflow.keras.layers.Dense(32, activation="relu"),
-        tensorflow.keras.layers.Dense(1),
+        Dense(512, activation="relu", input_dim=73),
+        tensorflow.keras.layers.BatchNormalization(),
+        Dense(512 // 2, activation="relu"),
+        tensorflow.keras.layers.BatchNormalization(),
+        Dense(512 // 4, activation="relu"),
+        tensorflow.keras.layers.BatchNormalization(),
+        Dense(512 // 8, activation="relu"),
+        tensorflow.keras.layers.BatchNormalization(),
+        Dense(32, activation="relu"),
+        tensorflow.keras.layers.BatchNormalization(),
+        Dense(1),
     ]
 )
+# model = tensorflow.keras.models.Sequential(
+#     [
+#         tensorflow.keras.layers.Dense(
+#             128, activation="relu", input_dim=73,
+#         ),
+#         tensorflow.keras.layers.Dense(128 // 2, activation="relu"),
+#         tensorflow.keras.layers.Dense(128 // 4, activation="relu"),
+#         tensorflow.keras.layers.Dense(128 // 8, activation="relu"),
+#         tensorflow.keras.layers.Dense(32, activation="relu"),
+#         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
+# model.summary() #Print model Summary
 
-model.compile(loss= "mean_squared_error" , optimizer="adam", metrics=["mean_squared_error"])
-f_train = np.asarray(f_train).astype(np.float32)
+model.compile(
+    loss="mean_squared_error", optimizer="adam", metrics=["mean_squared_error"]
+)
+f_train = np.asarray(x_train).astype(np.float32)
 y = np.asarray(y).astype(np.float32)
 model.fit(f_train, y, epochs=100)
 
@@ -107,11 +127,11 @@ model.fit(f_train, y, epochs=100)
 # dev0_predicted = regr_trans.predict(dev_df)
 # test_A_predicted = regr_trans.predict(test_A_df)
 
-# dev0_predicted = model.predict(dev_df)
+dev0_predicted = model.predict(dev_train)
 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)
+# 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)

run2.py

@@ -0,0 +1,50 @@
+import pandas as pd
+
+import tensorflow.keras
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import Dense
+
+in_columns = ["id_stacji", "nazwa_stacji", "typ_zbioru", "rok", "miesiąc"]
+df = pd.read_csv("train/in.tsv", names=in_columns, sep="\t")
+df_test = pd.read_csv("dev-0/in.tsv", names=in_columns, sep="\t")
+
+df = pd.concat([df, df_test])
+df = df.drop(["nazwa_stacji", "typ_zbioru"], axis=1)
+x = pd.get_dummies(df, columns=["id_stacji", "rok", "miesiąc"])
+
+x = x.iloc[:-600]
+y = pd.read_csv("train/expected.tsv", sep="\t", names=["rainfall"])
+
+model = Sequential(
+    [
+        Dense(512, activation="relu", input_dim=73),
+        tensorflow.keras.layers.BatchNormalization(),
+        Dense(512 // 2, activation="relu"),
+        tensorflow.keras.layers.BatchNormalization(),
+        Dense(512 // 4, activation="relu"),
+        tensorflow.keras.layers.BatchNormalization(),
+        Dense(512 // 8, activation="relu"),
+        tensorflow.keras.layers.BatchNormalization(),
+        Dense(32, activation="relu"),
+        tensorflow.keras.layers.BatchNormalization(),
+        Dense(1),
+    ]
+)
+
+model.compile(
+    loss="mean_squared_error", optimizer="adam", metrics=["mean_squared_error"]
+)
+model.fit(x, y, epochs=100)
+
+x_test = pd.read_csv("test-A/in.tsv", sep="\t", names=in_columns)
+df_train = pd.read_csv("train/in.tsv", names=in_columns, sep="\t")
+
+x_test = pd.concat([x_test, df_train])
+x_test = x_test.drop(["nazwa_stacji", "typ_zbioru"], axis=1)
+x_test = pd.get_dummies(x_test, columns=["id_stacji", "rok", "miesiąc"])
+
+x_test = x_test.iloc[:-8760]
+pred = model.predict(x_test)
+
+out = pd.DataFrame(pred)
+out.to_csv("test-A/out.tsv", sep="\t", header=False, index=False)