shift_daily_article_counts

shift_daily_article_counts.txt

def get_supervised_df(df, issue, maxlag=1):
  
  original = df.copy()
  
  #for each day of lag, we add a new column to the dataframe with the previous values
  for i in range(maxlag):
    print(i)
    original= pd.concat([original, df.shift(i+1).add_suffix("_(t-%s)"%(i+2))], axis=1).dropna()

  #save original issue to add back in
  myIssue = original[issue]
  
  original = original.shift().dropna()
 
  rename_dict = {}
  
  #I guess I shifted the first layer here, don't remember why
  for column in df:
    rename_dict[column] = column+"(t-1)"
  original.rename(columns=rename_dict,inplace=True)
  
  #put the original issue back in
  original[issue] = myIssue
  
  return original.dropna()