#!/usr/bin/env python
# coding: utf-8

# In[7]:


get_ipython().run_line_magic('matplotlib', 'inline')

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

pd.set_option('display.mpl_style', 'default')
plt.rcParams['figure.figsize'] = (15, 3)
plt.rcParams['font.family'] = 'sans-serif'


# We saw earlier that pandas is really good at dealing with dates. It is also amazing with strings! We're going to go back to our weather data from Chapter 5, here.

# In[8]:


weather_2012 = pd.read_csv('../data/weather_2012.csv', parse_dates=True, index_col='Date/Time')
weather_2012[:5]


# # 6.1 String operations

# You'll see that the 'Weather' column has a text description of the weather that was going on each hour. We'll assume it's snowing if the text description contains "Snow".
# 
# pandas provides vectorized string functions, to make it easy to operate on columns containing text. There are some great [examples](http://pandas.pydata.org/pandas-docs/stable/basics.html#vectorized-string-methods) in the documentation.

# In[9]:


weather_description = weather_2012['Weather']
is_snowing = weather_description.str.contains('Snow')


# This gives us a binary vector, which is a bit hard to look at, so we'll plot it.

# In[10]:


# Not super useful
is_snowing[:5]


# In[11]:


# More useful!
is_snowing.plot()


# # 6.2 Use resampling to find the snowiest month

# If we wanted the median temperature each month, we could use the `resample()` method like this:

# In[12]:


weather_2012['Temp (C)'].resample('M', how=np.median).plot(kind='bar')


# Unsurprisingly, July and August are the warmest.

# So we can think of snowiness as being a bunch of 1s and 0s instead of `True`s and `False`s:

# In[13]:


is_snowing.astype(float)[:10]


# and then use `resample` to find the percentage of time it was snowing each month

# In[14]:


is_snowing.astype(float).resample('M', how=np.mean)


# In[15]:


is_snowing.astype(float).resample('M', how=np.mean).plot(kind='bar')


# So now we know! In 2012, December was the snowiest month. Also, this graph suggests something that I feel -- it starts snowing pretty abruptly in November, and then tapers off slowly and takes a long time to stop, with the last snow usually being in April or May.

# # 6.3 Plotting temperature and snowiness stats together

# We can also combine these two statistics (temperature, and snowiness) into one dataframe and plot them together:

# In[16]:


temperature = weather_2012['Temp (C)'].resample('M', how=np.median)
is_snowing = weather_2012['Weather'].str.contains('Snow')
snowiness = is_snowing.astype(float).resample('M', how=np.mean)

# Name the columns
temperature.name = "Temperature"
snowiness.name = "Snowiness"


# We'll use `concat` again to combine the two statistics into a single dataframe.

# In[17]:


stats = pd.concat([temperature, snowiness], axis=1)
stats


# In[18]:


stats.plot(kind='bar')


# Uh, that didn't work so well because the scale was wrong. We can do better by plotting them on two separate graphs:

# In[19]:


stats.plot(kind='bar', subplots=True, figsize=(15, 10))


# <style>
#     @font-face {
#         font-family: "Computer Modern";
#         src: url('http://mirrors.ctan.org/fonts/cm-unicode/fonts/otf/cmunss.otf');
#     }
#     div.cell{
#         width:800px;
#         margin-left:16% !important;
#         margin-right:auto;
#     }
#     h1 {
#         font-family: Helvetica, serif;
#     }
#     h4{
#         margin-top:12px;
#         margin-bottom: 3px;
#        }
#     div.text_cell_render{
#         font-family: Computer Modern, "Helvetica Neue", Arial, Helvetica, Geneva, sans-serif;
#         line-height: 145%;
#         font-size: 130%;
#         width:800px;
#         margin-left:auto;
#         margin-right:auto;
#     }
#     .CodeMirror{
#             font-family: "Source Code Pro", source-code-pro,Consolas, monospace;
#     }
#     .text_cell_render h5 {
#         font-weight: 300;
#         font-size: 22pt;
#         color: #4057A1;
#         font-style: italic;
#         margin-bottom: .5em;
#         margin-top: 0.5em;
#         display: block;
#     }
#     
#     .warning{
#         color: rgb( 240, 20, 20 )
#         }