from __future__ import print_function, division

%matplotlib inline
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# use seaborn plotting defaults
import seaborn as sns; sns.set()

# !curl -O http://academic.udayton.edu/kissock/http/Weather/gsod95-current/NOOSLO.txt
# !mv NOOSLO.txt data

data = pd.read_csv('data/NOOSLO.txt', delim_whitespace=True,
                   names=['month', 'day', 'year', 'degF'])
data.describe()

# Filter bad years
data = data[data.year > 200]

# Filter missing data
data = data[data.degF > -99]

data.describe()

# Create a date index
YMD = 10000 * data.year + 100 * data.month + data.day
data.index = pd.to_datetime(YMD, format='%Y%m%d').astype('datetime64[ns]')
data.head()