bhishanpdl

#!python
# -*- coding: utf-8 -*-#
"""
Create fitsfile.

Author : Bhishan Poudel
Date   : Sep 4, 2018

Combine two fitsfile keeping their fitsheaders.

bhishanpdl

ax = users['gender'].value_counts().plot(kind='barh')
for p in ax.patches:
    ax.annotate(str(int(p.get_width())), (p.get_x() + p.get_width(), p.get_y()), xytext=(-2, 4), textcoords='offset points', horizontalalignment='right')

bhishanpdl

ax = users['gender'].value_counts().plot(kind='bar')
for p in ax.patches:
    ax.annotate(np.round(p.get_height(), decimals=2), 
                (p.get_x()+p.get_width()/2.,
                 p.get_height()), ha='center', 
                va='center', xytext=(0, 10), 
                textcoords='offset points')

bhishanpdl

def clean_data(data):    
    """
    Clean the pandas dataframe.

    data: pandas dataframe 

    return: cleaned dataframe


    1. Make column names lowercase and underscored.

bhishanpdl

%%bash

cat > out.csv << EOL
lines
EOL

bhishanpdl

1. Clean data

READ THE DATA CLEAN CODE

bhishanpdl

import pandas as pd
import calendar

# Ref: https://docs.python.org/2/library/datetime.html


df['release_year'] = pd.to_datetime(df['release_date'], format='%m/%d/%y')

df['release_month'] = df['release_year'].dt.month

bhishanpdl

import pandas as pd
import string

df = pd.DataFrame({'c0':range(1,10), 'c1': list(string.ascii_letters[0:9])})
df2 = df.iloc[[0, -1]]

# first and last 10
df = pd.concat([df.head(10), df.tail(10)])

bhishanpdl

%matplotlib inline

from pandas import Series
import matplotlib.pyplot as plt

heights = Series(
    [165, 170, 195, 190, 170, 
     170, 185, 160, 170, 165, 
     185, 195, 185, 195, 200, 
     195, 185, 180, 185, 195],

bhishanpdl

df.set_index('First_col').T.plot(kind='bar', stacked=True,figsize=(16,8))