notebook.community

Edit and run



In [2]:

    
import sys
sys.path.insert(0, '../Code/')

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import load_data



In [3]:

    
data = load_data.import_cleaned_data('train')









    



Tokenization took: 31.64 ms
Type conversion took: 70.70 ms
Parser memory cleanup took: 0.21 ms
Tokenization took: 15.32 ms
Type conversion took: 61.11 ms
Parser memory cleanup took: 0.04 ms
Tokenization took: 16.28 ms
Type conversion took: 65.80 ms
Parser memory cleanup took: 0.14 ms
Tokenization took: 0.14 ms
Type conversion took: 2.45 ms
Parser memory cleanup took: 0.00 ms



In [4]:

    
def plot_categorical_data(data):
    """
    
    """









    Out[4]:






  
    
      
      site_name
      posa_continent
      user_location_country
      user_location_region
      user_location_city
      orig_destination_distance
      user_id
      is_mobile
      is_package
      channel
      ...
      month_action
      day_action
      hour_action
      minute_action
      year_checkin
      month_checkin
      day_checkin
      year_checkout
      month_checkout
      day_checkout
    
  
  
    
      0
      2
      3
      66
      348
      48862
      2234.2641
      12
      0
      1
      9
      ...
      8
      11
      7
      46
      1
      8
      27
      1
      8
      31
    
    
      1
      2
      3
      66
      348
      48862
      2234.2641
      12
      0
      1
      9
      ...
      8
      11
      8
      22
      1
      8
      29
      1
      9
      2
    
    
      2
      2
      3
      66
      348
      48862
      2234.2641
      12
      0
      0
      9
      ...
      8
      11
      8
      24
      1
      8
      29
      1
      9
      2
    
    
      3
      2
      3
      66
      442
      35390
      913.1932
      93
      0
      0
      3
      ...
      8
      9
      18
      5
      1
      11
      23
      1
      11
      28
    
    
      4
      2
      3
      66
      442
      35390
      913.6259
      93
      0
      0
      3
      ...
      8
      9
      18
      8
      1
      11
      23
      1
      11
      28
    
  

5 rows × 32 columns



In [ ]:

	site_name	posa_continent	user_location_country	user_location_region	user_location_city	orig_destination_distance	user_id	is_package	channel	...	month_action	day_action	hour_action	minute_action	year_checkin	month_checkin	day_checkin	year_checkout	month_checkout	day_checkout
0	2	3	66	348	48862	2234.2641	12	1	9	...	8	11	7	46	1	8	27	1	8	31
1	2	3	66	348	48862	2234.2641	12	1	9	...	8	11	8	22	1	8	29	1	9	2
2	2	3	66	348	48862	2234.2641	12	0	9	...	8	11	8	24	1	8	29	1	9	2
3	2	3	66	442	35390	913.1932	93	0	3	...	8	9	18	5	1	11	23	1	11	28
4	2	3	66	442	35390	913.6259	93	0	3	...	8	9	18	8	1	11	23	1	11	28