final attempt23

run5.py

@@ -21,9 +21,11 @@ y = pd.read_csv("train/expected.tsv", sep="\t", names=["rainfall"])
 df["rainfall"] = y["rainfall"]
 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")
-
+y2 = pd.read_csv("dev-0/expected.tsv", sep="\t", names=["rainfall"])
 x_test = pd.concat([x_test, df_train])
 
+y = pd.concat([y, y2])
+
 # grouped_multiple_years = df.groupby(['id_stacji', 'rok']).agg({'rainfall': ['mean', 'min', 'max']})
 # grouped_multiple_months = df.groupby(['id_stacji', 'miesiąc']).agg({'rainfall': ['mean', 'min', 'max']})
 # flat = grouped_multiple_years.reset_index()
@@ -46,7 +48,6 @@ x_test = pd.concat([x_test, df_train])
 
 x = pd.get_dummies(df, columns=["id_stacji", "rok", "miesiąc"])
 x = x.drop(["nazwa_stacji", "typ_zbioru", "rainfall"], axis=1)
-x = x.iloc[:-600]
 
 model = Sequential(
     [
@@ -61,6 +62,7 @@ model = Sequential(
         Dense(64, activation="relu"),
         # tensorflow.keras.layers.BatchNormalization(),
         Dense(32, activation="relu"),
+        Dense(16, activation="relu"),
         # tensorflow.keras.layers.BatchNormalization(),
         Dense(1, activation="linear"),
     ]
@@ -82,8 +84,6 @@ model.compile(
 # estimator = KerasRegressor(build_fn=model, epochs=100, batch_size=10, verbose=0)
 # estimator.fit(x, y)
 model.fit(x, y, epochs=100)
-exit()
-
 
 x_test = x_test.drop(["nazwa_stacji", "typ_zbioru"], axis=1)
 x_test = pd.get_dummies(x_test, columns=["id_stacji", "rok", "miesiąc"])
@@ -91,4 +91,4 @@ x_test = x_test.iloc[:-8760]
 pred = model.predict(x_test)
 # pred = estimator.predict(x_test)
 out = pd.DataFrame(pred)
-out.to_csv("test-A/out2.tsv", sep="\t", header=False, index=False)
+out.to_csv("test-A/out.tsv", sep="\t", header=False, index=False)