from utils import preprocess, feature_engineer
import pandas as pd
import numpy as np
from sklearn.preprocessing import scale
from sklearn.model_selection import train_test_split
from keras.models import Sequential
from keras.layers import Dense
from sklearn.metrics import mean_squared_error

df = pd.read_csv('NYC_taxi.csv', parse_dates=['pickup_datetime'], nrows=500000)

df = preprocess(df)
df = feature_engineer(df)