# Based on https://www.kaggle.com/antgoldbloom/exploring-climate-change-data

import pandas as pd
import sys

# Check usage
if len(sys.argv) < 2:
    print("Usage: %s <csv file>" % sys.argv[0])
    sys.exit()

csvfile = sys.argv[1]

# Sort all cities on average temperature
dfTempByCity = pd.read_csv(csvfile,index_col='dt',parse_dates=[0])
cities_2012_avg = dfTempByCity[dfTempByCity.index.year == 2012][['City','Country','AverageTemperature']].groupby(['City','Country']).mean().sort_values('AverageTemperature',ascending=False)

print("Cities with highest average temperature in 2012:")
print(cities_2012_avg.head())

print("")

print("Cities with lowest average temperature in 2012:")
print(cities_2012_avg.tail())

#Temperature in Groningen using a 12 month rolling mean to smooth out seasonality
plot = pd.Series.rolling(dfTempByCity[dfTempByCity['City'] == 'Groningen']['AverageTemperature'],window=12).mean().plot(x=dfTempByCity.index)
plot.get_figure().savefig('plot.png')