import pandas as pd
import numpy as np

from tensorflow import keras

device = 'cpu'

data = pd.read_csv("data_train", sep=',', error_bad_lines=False).dropna()
X = data.loc[:,data.columns == "2805317"].astype(int)
y = data.loc[:,data.columns == "198909"].astype(int)


def NormalizeData(data):
    return (data - np.min(data)) / (np.max(data) - np.min(data))


X = NormalizeData(X)
y = NormalizeData(y)


model = keras.Sequential([
    keras.layers.Dense(512,input_dim = X.shape[1],kernel_initializer='normal', activation='relu'),
    keras.layers.Dense(512,kernel_initializer='normal', activation='relu'),
    keras.layers.Dense(256,kernel_initializer='normal', activation='relu'),
    keras.layers.Dense(256,kernel_initializer='normal', activation='relu'),
    keras.layers.Dense(128,kernel_initializer='normal', activation='relu'),
    keras.layers.Dense(1,kernel_initializer='normal', activation='linear'),
])

model.compile(loss='mean_absolute_error', optimizer='adam', metrics=['mean_absolute_error'])

model.fit(X, y, epochs=30, validation_split = 0.3)

data = pd.read_csv("data_test", sep=',', error_bad_lines=False).dropna()
X_test = data.loc[:,data.columns == "2805317"].astype(int)
y_test = data.loc[:,data.columns == "198909"].astype(int)

X_test = NormalizeData(X_test)
y_test = NormalizeData(y_test)

prediction = model.predict(X_test)

f = open("predictions.txt", "w")
for (pred, test) in zip(prediction, y_test.values):
    f.write("predicted: %s expected: %s\n" % (str(pred), str(test)))