from operations import Operations ops = Operations() #Create the dataframe from the lines RDD df = ops.create_dataframe(lines, sqlContext) #Clean the 'pagename' column of encoded characters df = ops.clean_string_column(df, 'pagename') #Add columns for hour, day, month, year from the file name df = ops.append_date_columns(df) #Group by timeframes hour_df, day_df, month_df, year_df = ops.aggregate_times(df) #Create tokens from the pagename hour_df = ops.append_tokens(hour_df) #Add term frequency and inverse document frequency hour_df = ops.append_tf_idf(hour_df) #Create ranking hour_df, day_df, month_df, year_df = ops.append_ranks(hour_df, day_df, month_df, year_df) #Get the top 200 for each timeframe top_hourly = hour_df.filter(hour_df['hour_rank']<201) top_daily = day_df.filter(day_df['day_rank']<201) top_monthly = month_df.filter(month_df['month_rank']<201) top_yearly = year_df.filter(year_df['year_rank']<201) #Create files on s3 with the results ops.make_plot_csv(top_hourly,"hourly") ops.make_plot_csv(top_daily,"daily") ops.make_plot_csv(top_monthly,"monthly") ops.make_plot_csv(top_yearly,"yearly")
