import numpy
import pandas
from keras.models import Sequential
from keras.layers import Dense
from keras.wrappers.scikit_learn import KerasRegressor
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import KFold
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline

dataframe = pandas.read_csv('data/tmdb/train_processed.csv')
dataframe.drop('id', axis=1, inplace=True)

Y = dataframe['revenue'].values
dataframe.drop(columns=['revenue'], inplace=True)
X = dataframe.values

def baseline_model():
  model = Sequential()
  model.add(Dense(13, input_dim=3, kernel_initializer='normal', activation='relu'))
  model.add(Dense(1, kernel_initializer='normal'))
  model.compile(loss='mean_squared_error', optimizer='adam')
  return model

seed = 7
numpy.random.seed(seed)

estimators = []
estimators.append(('standardize', StandardScaler()))
estimators.append(('mlp', KerasRegressor(build_fn=baseline_model, epochs=100, batch_size=5, verbose=1)))
pipeline = Pipeline(estimators)
kfold = KFold(n_splits=10, random_state=seed)
results = cross_val_score(pipeline, X, Y, cv=kfold)
print("Result: %.2f (%.2f) MSE" % (results.mean(), results.std()))