In [1]:

%pylab inline

Populating the interactive namespace from numpy and matplotlib

In [2]:

import dataiku
from dataiku import pandasutils as pdu
import pandas as pd

In [3]:

# Example: load a DSS dataset as a Pandas dataframe
dataset_orders = dataiku.Dataset("orders")
df = dataset_orders.get_dataframe()
df.head()

Out[3]:

	order_date	pages_visited	order_id	customer_id	tshirt_category	tshirt_price	tshirt_quantity
0	2016/09/04	9	HTS-038040-0002	038040	White T-Shirt M	20.0	1
1	2014/11/14	11	HTS-801797-0001	801797	White T-Shirt M	20.0	1
2	2017/02/26	10	HTS-vft1eu-0003	vft1eu	White T-Shirt F	18.0	3
3	2013/12/01	10	HTS-914324-0001	914324	Wh Tshirt F	18.0	1
4	2015/10/22	12	HTS-88ua9r-0001	88ua9r	White T-Shirt M	20.0	1

In [4]:

pdu.audit(df)

Out[4]:

	_a_variable	_b_data_type	_c_cardinality	_e_sample_values
0	order_date	object	1431	[2016/09/04, 2014/11/14]
1	pages_visited	int64	26	[9, 11]
2	order_id	object	26511	[HTS-038040-0002, HTS-801797-0001]
3	customer_id	object	11651	[038040, 801797]
4	tshirt_category	object	10	[White T-Shirt M, White T-Shirt F]
5	tshirt_price	float64	6	[20.0, 18.0]
6	tshirt_quantity	int64	28	[1, 3]