cheat-sheet.txt

                                Welcome!


   1. Install Pandas and the IPython Notebook

      The Anaconda distribution includes Pandas built-in:
      http://continuum.io/downloads


   2. Download and unzip "Pandas-Tutorial.zip" from

      https://github.com/brandon-rhodes/pycon-pandas-tutorial/releases


   3. Start the IPython Notebook and visit the "pandas-tutorial"
      folder from inside the .zip



  len(df)       series + value    df[df.c == value]
  df.head()     series + series2  df[(df.c >= value) & (df.d < value)]
  df.tail()     series.notnull()  df[(df.c < value) | (df.d != value)]
  df.COLUMN     series.isnull()   df.sort('column')
  df['COLUMN']  series.order()    df.sort(['column1', 'column2'])




                        import sys
                        reload(sys)
                        sys.setdefaultencoding('utf-8')






      http://continuum.io/downloads

      https://github.com/brandon-rhodes/pycon-pandas-tutorial/releases



  len(df)       series + value    df[df.c == value]
  df.head()     series + series2  df[(df.c >= value) & (df.d < value)]
  df.tail()     series.notnull()  df[(df.c < value) | (df.d != value)]
  df.COLUMN     series.isnull()   df.sort('column')
  df['COLUMN']  series.order()    df.sort(['column1', 'column2'])

s.str.len()        s.value_counts() df[['column1', 'column2']]
s.str.contains()   s.sort_index() df.plot(x='a', y='b', kind='scatter')
s.str.startswith() s.plot(...)      df.plot(x='a', y='b', kind='bar')


                        import sys
                        reload(sys)
                        sys.setdefaultencoding('utf-8')



  len(df)       series + value    df[df.c == value]
  df.head()     series + series2  df[(df.c >= value) & (df.d < value)]
  df.tail()     series.notnull()  df[(df.c < value) | (df.d != value)]
  df.COLUMN     series.isnull()   df.sort('column')
  df['COLUMN']  series.order()    df.sort(['column1', 'column2'])

  s.str.len()        s.value_counts()
  s.str.contains()   s.sort_index()   df[['column1', 'column2']]
  s.str.startswith() s.plot(...)      df.plot(x='a', y='b', kind='bar')

  df.set_index('a').sort_index()        df.loc['value']
  df.set_index(['a', 'b']).sort_index() df.loc[('v','u')]
  df.groupby('column')                  .size() .mean() .min() .max()
  df.groupby(['column1', 'column2'])    .agg(['min', 'max'])



  "The Pink Panther"


  brandon@rhodesmill.org


  len(df)       series + value    df[df.c == value]
  df.head()     series + series2  df[(df.c >= value) & (df.d < value)]
  df.tail()     series.notnull()  df[(df.c < value) | (df.d != value)]
  df.COLUMN     series.isnull()   df.sort('column')
  df['COLUMN']  series.order()    df.sort(['column1', 'column2'])

  s.str.len()        s.value_counts()
  s.str.contains()   s.sort_index()   df[['column1', 'column2']]
  s.str.startswith() s.plot(...)      df.plot(x='a', y='b', kind='bar')

  df.set_index('a').sort_index()        df.loc['value']
  df.set_index(['a', 'b']).sort_index() df.loc[('v','u')]
  df.groupby('column')                  .size() .mean() .min() .max()
  df.groupby(['column1', 'column2'])    .agg(['min', 'max'])

  df.unstack()
  df.stack()
  df.fillna(value)
  s.fillna(value)



  len(df)       series + value    df[df.c == value]
  df.head()     series + series2  df[(df.c >= value) & (df.d < value)]
  df.tail()     series.notnull()  df[(df.c < value) | (df.d != value)]
  df.COLUMN     series.isnull()   df.sort('column')
  df['COLUMN']  series.order()    df.sort(['column1', 'column2'])

  s.str.len()        s.value_counts()
  s.str.contains()   s.sort_index()    df[['column1', 'column2']]
  s.str.startswith() s.plot(...)       df.plot(x='a', y='b', kind='bar')

  df.set_index('a').sort_index()        df.loc['value']
  df.set_index(['a', 'b']).sort_index() df.loc[('v','u')]
  df.groupby('column')                  .size() .mean() .min() .max()
  df.groupby(['column1', 'column2'])    .agg(['min', 'max'])

  df.unstack()      s.dt.year
  df.stack()        s.dt.month
  df.fillna(value)  s.dt.day
  s.fillna(value)   s.dt.dayofweek



  len(df)       series + value    df[df.c == value]
  df.head()     series + series2  df[(df.c >= value) & (df.d < value)]
  df.tail()     series.notnull()  df[(df.c < value) | (df.d != value)]
  df.COLUMN     series.isnull()   df.sort('column')
  df['COLUMN']  series.order()    df.sort(['column1', 'column2'])

  s.str.len()        s.value_counts()
  s.str.contains()   s.sort_index()    df[['column1', 'column2']]
  s.str.startswith() s.plot(...)       df.plot(x='a', y='b', kind='bar')

  df.set_index('a').sort_index()        df.loc['value']
  df.set_index(['a', 'b']).sort_index() df.loc[('v','u')]
  df.groupby('column')                  .size() .mean() .min() .max()
  df.groupby(['column1', 'column2'])    .agg(['min', 'max'])

  df.unstack()      s.dt.year       df.merge(df2, how='outer', ...)
  df.stack()        s.dt.month      df.rename(columns={'a': 'y', 'b': 'z'})
  df.fillna(value)  s.dt.day        pd.concat([df1, df2])
  s.fillna(value)   s.dt.dayofweek






                          Thanks!

                      Any questions?

Local variables:
 mode:text
 mode:page
End: