import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
data = pd.read_csv('data/nyc_data.csv', parse_dates=['pickup_datetime',
                                                     'dropoff_datetime'])
fare = pd.read_csv('data/nyc_fare.csv', parse_dates=['pickup_datetime'])

data[['trip_distance', 'trip_time_in_secs']].head(3)

data.loc[0]

data.loc[[0, 100000]]

data.loc[1000:2000:10,
         ['trip_distance', 'trip_time_in_secs']]

data.loc[data.trip_distance>50]

from ipywidgets import interact

@interact
def show_nrows(distance_threshold=(0, 200)):
    return len(data.loc[data.trip_distance > distance_threshold])

data['trip_time_in_mins'] = data.trip_time_in_secs / 60.0

data[['trip_time_in_secs', 'trip_time_in_mins']].head(3)

a = data.trip_distance[:5]
a

b = data.trip_distance[2:6]
b

a + b

data.medallion.head(3)

data.medallion.str.slice(0, 4).head(3)

data.pickup_datetime.dt.dayofweek[::200000]

day_p = data.pickup_datetime.dt.day
day_d = data.dropoff_datetime.dt.day
selection = (day_p != day_d)
print(len(data.loc[selection]))
data.loc[selection].head(3)