mmatkinson

Interactive Tutorials

• https://learngitbranching.js.org/

End-To-end Tutorial

• (Pycon 2016 - 3 hrs) : https://www.youtube.com/watch?v=RrdECLvHW6g

Command line tutorial

• https://www.youtube.com/watch?v=HVsySz-h9r4

mmatkinson

-- show running queries (pre 9.2)
SELECT procpid, age(query_start, clock_timestamp()), usename, current_query 
FROM pg_stat_activity 
WHERE current_query != '<IDLE>' AND current_query NOT ILIKE '%pg_stat_activity%' 
ORDER BY query_start desc;

-- show running queries (9.2)
SELECT pid, age(query_start, clock_timestamp()), usename, query 
FROM pg_stat_activity 
WHERE query != '<IDLE>' AND query NOT ILIKE '%pg_stat_activity%' 

mmatkinson

**Convert .ipynb to Slides**
cd "test"
ipython nbconvert "test.ipynb" --to slides --reveal-prefix "http://cdn.jsdelivr.net/reveal.js/2.6.2" --post serve --config slides_config.py

* To print slides add ?print-pdf at the end of the URL and print

**Convert .ipynb to LaTex/PDF**
ipython nbconvert MyFirstNotebook.ipynb --to latex --post PDF

**Convert .ipynb to HTML**

mmatkinson

mmatkinson

mmatkinson

"""Google spreadsheet related.
Packages required: oauth2client, google-api-python-client
* https://gist.github.com/miohtama/f988a5a83a301dd27469
"""

from oauth2client.service_account import ServiceAccountCredentials
from apiclient import discovery


def get_credentials(scopes: list) -> ServiceAccountCredentials:

mmatkinson

def df_to_ddl(df, tablename='test.mytable'):
    data_dtypes = df.dtypes.reset_index().rename(columns = {'index':'colname',0:'datatype'})

    # Map pandas datatypes into SQL 
    data_dtypes['sql_dtype'] = data_dtypes.datatype.astype(str).map(
                            {'object':'varchar(24)',
                             'float64':'float', 
                             'int64':'int', 
                             'bool':'boolean'}   )

mmatkinson

import pandas as pd 

def df_diff(index_cols, data1, data2, lsuffix='_1'):
  """
  usage: 
  comparisondf=  df_diff( ['unique_id','date'],  current_df, new_df, lsuffix='_curr')
  
  retuns: 
  single dataframe with index_cols on the index, as well as all other variables stacked on the index, and the 
  values in each dataframe along the columns. 

mmatkinson

# For gensim
from itertools import groupby
import gensim


class VectorizedCorpus(object):
    """
    Helper Class for using Sklearn Vectorizers with gensim's LDA model
    handles transformations between gensim corpus / bow representations and sklearn matrix
    

mmatkinson

#List unique values in a DataFrame column
pd.unique(df.column_name.ravel())

#Convert Series datatype to numeric, getting rid of any non-numeric values
df['col'] = df['col'].astype(str).convert_objects(convert_numeric=True)

#Grab DataFrame rows where column has certain values
valuelist = ['value1', 'value2', 'value3']
df = df[df.column.isin(value_list)]