jad55a swiry5

run4.py

@@ -0,0 +1,101 @@
+import pandas as pd
+
+import tensorflow.keras
+
+import numpy as np
+import pandas as pd
+import xgboost as xg
+import keras_tuner as kt
+
+
+import tensorflow.keras
+from sklearn.preprocessing import PolynomialFeatures
+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])
+x = pd.get_dummies(df, columns=["id_stacji", "rok", "miesiąc"])
+x = x.drop(["nazwa_stacji", "typ_zbioru"], axis=1)
+x = x.iloc[:-600]
+y = pd.read_csv("train/expected.tsv", sep="\t", names=["rainfall"])
+from keras_tuner import HyperModel
+
+
+class ANNHyperModel(HyperModel):
+
+    def build(self, hp):
+        model = tensorflow.keras.Sequential()
+        # Tune the number of units in the first Dense layer
+        # Choose an optimal value between 32-512
+        hp_units1 = hp.Int('units1', min_value=32, max_value=512, step=32)
+        hp_units2 = hp.Int('units2', min_value=32, max_value=512, step=32)
+        hp_units3 = hp.Int('units3', min_value=32, max_value=512, step=32)
+        hp_units4 = hp.Int('units4', min_value=32, max_value=512, step=32)
+        hp_units5 = hp.Int('units5', min_value=32, max_value=512, step=32)
+        model.add(Dense(units=hp_units1, activation='relu'))
+        model.add(tensorflow.keras.layers.Dense(units=hp_units2, activation='relu'))
+        model.add(tensorflow.keras.layers.Dense(units=hp_units3, activation='relu'))
+        model.add(tensorflow.keras.layers.Dense(units=hp_units4, activation='relu'))
+        model.add(tensorflow.keras.layers.Dense(units=hp_units5, activation='relu'))
+        model.add(Dense(1, kernel_initializer='normal', activation='linear'))
+
+        # Tune the learning rate for the optimizer
+        # Choose an optimal value from 0.01, 0.001, or 0.0001
+        hp_learning_rate = hp.Choice('learning_rate',
+                                     values=[1e-2, 1e-3, 1e-4])
+
+        model.compile(
+            optimizer=tensorflow.keras.optimizers.Adam(learning_rate=hp_learning_rate),
+            loss="mean_squared_error",
+            metrics=["mean_squared_error"]
+        )
+
+        return model
+
+
+hypermodel = ANNHyperModel()
+
+tuner = kt.Hyperband(
+    hypermodel,
+    objective='mean_squared_error',
+    max_epochs=100,
+    factor=3,
+    directory='keras_tuner_dir',
+    project_name='keras_tuner_demo2'
+)
+#po#ly = PolynomialFeatures(2, interaction_only=True)
+#x = poly.fit_transform(x)
+
+tuner.search(x, y, epochs=100)
+
+for h_param in [f"units{i}" for i in range(1,4)] + ['learning_rate']:
+  print(h_param, tuner.get_best_hyperparameters()[0].get(h_param))
+
+best_model = tuner.get_best_models()[0]
+best_model.build(x.shape)
+best_model.summary()
+
+best_model.fit(
+    x,
+    y,
+    epochs=100,
+    batch_size=64
+)
+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]
+#poly = PolynomialFeatures(2, interaction_only=True)
+#x_test= poly.fit_transform(x_test)
+pred = best_model.predict(x_test)
+out = pd.DataFrame(pred)
+out.to_csv("test-A/out.tsv", sep="\t", header=False, index=False)
+