import pandas as pd

# some display options to make figures bigger
# hide this
pd.set_option('display.max_columns', 15)
pd.set_option('display.line_width', 400)
pd.set_option('display.mpl_style', 'default')
rcParams['figure.figsize'] = (14, 7)
import matplotlib
font = {'family' : 'normal',
        'weight' : 'bold',
        'size'   : 22}

matplotlib.rc('font', **font)

bike_data = pd.read_csv("./2012.csv")
bike_data[:5]

bike_data = pd.read_csv("./2012.csv", encoding='latin1', sep=';', index_col='Date', parse_dates=True, dayfirst=True)

# Get rid of missing columns
bike_data = bike_data.dropna(axis=1)
# Only use 3 of the columns so it all fits on the screen


bike_data = bike_data[['Berri 1', u'Côte-Sainte-Catherine', 'Maisonneuve 1']]
bike_data[:5]

bike_data[:3]

 bike_data.plot()

bike_data.median()

bike_data.median().plot(kind='bar')

# column slice
column_slice = bike_data[['Berri 1', 'Maisonneuve 1']]
# row slice
column_slice[:3]

column_slice.plot()

bike_data['weekday'] = bike_data.index.weekday
bike_data.head()

counts_by_day = bike_data.groupby('weekday').aggregate(numpy.sum)
counts_by_day


counts_by_day.index = ['Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday']
counts_by_day.plot()

bike_data['Berri 1'].plot()

def get_weather_data(year):
    url_template = "http://climate.weather.gc.ca/climateData/bulkdata_e.html?format=csv&stationID=5415&Year={year}&Month={month}&timeframe=1&submit=Download+Data"
    # mctavish station: 10761, airport station: 5415
    data_by_month = []
    for month in range(1, 13):
        url = url_template.format(year=year, month=month)
        weather_data = pd.read_csv(url, skiprows=16, index_col='Date/Time', parse_dates=True).dropna(axis=1)
        weather_data.columns = map(lambda x: x.replace('\xb0', ''), weather_data.columns)
        weather_data = weather_data.drop(['Year', 'Day', 'Month', 'Time', 'Data Quality'], axis=1)
        data_by_month.append(weather_data.dropna())
    # Concatenate and drop any empty columns
    return pd.concat(data_by_month).dropna(axis=1, how='all').dropna()

weather_data = get_weather_data(2012)

weather_data[:5]

bike_data['mean temp'] = weather_data['Temp (C)'].resample('D', how='mean')

bike_data.head()

bike_data[['Berri 1', 'mean temp']].plot(subplots=True)

bike_data['Rain'] = weather_data['Weather'].str.contains('Rain').map(lambda x: int(x)).resample('D', how='mean')

bike_data[['Berri 1', 'Rain']].plot(subplots=True)

# Look at everything between May and September
summertime_data = bike_data['2012-05-01':'2012-09-01']

summertime_data['Berri 1'][:5] < 2500

summertime_data = bike_data['2012-05-01':'2012-09-01']
bad_days = summertime_data[summertime_data['Berri 1'] < 2500]
bad_days[['Berri 1', 'Rain', 'mean temp', 'weekday']]


julia = {'email': 'julia@jvns.ca', 'twitter': 'http://twitter.com/b0rk'}

print 'Email:', julia['email']
print 'Twitter:', julia['twitter']
print 'Slides: http://bit.ly/pyconca-pandas'