10: Apply TableVectorizer

This step used:

9: CallMethod 'assign'

This step was used by:

11: CallMethod 'groupby'

Where was this step created?

                
  File "/home/circleci/project/doc/conf.py", line 586, in <module>
    create_expression_report()
  File "/home/circleci/project/doc/expression_report.py", line 39, in create_expression_report
    vectorized_products = products.skb.apply(vectorizer, cols=s.all() - "basket_ID")

Estimator fitted in this step:

ApplyToFrame(cols=(all() - cols('basket_ID')),
             transformer=TableVectorizer(high_cardinality=MinHashEncoder(n_components=np.int64(9))))

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

ApplyToFrame

iFitted

Parameters

	transformer	TableVectoriz...=np.int64(9)))
	cols	(all() - cols('basket_ID'))
	keep_original	False
	rename_columns	'{}'

transformer: TableVectorizer

TableVectorizer(high_cardinality=MinHashEncoder(n_components=np.int64(9)))

numeric

PassThrough

Parameters

datetime

DatetimeEncoder

Parameters

	resolution	'hour'
	add_weekday	False
	add_total_seconds	True
	add_day_of_year	False
	periodic_encoding	None

low_cardinality

OneHotEncoder

?Documentation for OneHotEncoder

Parameters

	categories	'auto'
	drop	'if_binary'
	sparse_output	False
	dtype	'float32'
	handle_unknown	'ignore'
	min_frequency	None
	max_categories	None
	feature_name_combiner	'concat'

high_cardinality

MinHashEncoder

Parameters

	n_components	np.int64(9)
	ngram_range	(2, ...)
	hashing	'fast'
	minmax_hash	False
	n_jobs	None

Output of this step

Column	Column name	dtype	Unique values	Mean	Std	Min	Median	Max
0	basket_ID	Int64DType	61241 (56.0%)	3.59e+04	2.24e+04	0	35,203	76,543
1	item_0	Float32DType	70 (< 0.1%)	-2.03e+09	1.54e+08	-2.15e+09	-2.12e+09	-1.04e+09
2	item_1	Float32DType	46 (< 0.1%)	-1.92e+09	2.63e+08	-2.14e+09	-2.06e+09	-1.09e+09
3	item_2	Float32DType	57 (< 0.1%)	-1.98e+09	1.85e+08	-2.14e+09	-2.09e+09	-3.95e+08
4	item_3	Float32DType	52 (< 0.1%)	-2.06e+09	8.25e+07	-2.15e+09	-2.07e+09	-8.27e+08
5	item_4	Float32DType	63 (< 0.1%)	-2.02e+09	6.26e+07	-2.15e+09	-2.05e+09	-1.08e+09
6	item_5	Float32DType	61 (< 0.1%)	-1.99e+09	2.14e+08	-2.14e+09	-2.06e+09	-8.93e+08
7	item_6	Float32DType	67 (< 0.1%)	-1.77e+09	3.82e+08	-2.14e+09	-1.99e+09	-9.01e+07
8	item_7	Float32DType	60 (< 0.1%)	-1.97e+09	1.38e+08	-2.14e+09	-2.00e+09	-1.20e+09
9	item_8	Float32DType	64 (< 0.1%)	-1.98e+09	1.06e+08	-2.15e+09	-2.02e+09	-9.20e+08
10	cash_price	Float32DType	1280 (1.2%)	672.	714.	0.00	499.	1.83e+04
11	make_0	Float32DType	337 (0.3%)	-1.48e+09	7.40e+08	-2.15e+09	-1.72e+09	1.30e+09
12	make_1	Float32DType	323 (0.3%)	-1.20e+09	8.17e+08	-2.15e+09	-5.10e+08	1.23e+09
13	make_2	Float32DType	301 (0.3%)	-1.65e+09	3.86e+08	-2.15e+09	-1.52e+09	1.39e+09
14	make_3	Float32DType	301 (0.3%)	-1.79e+09	6.28e+08	-2.15e+09	-1.97e+09	6.60e+08
15	make_4	Float32DType	316 (0.3%)	-1.30e+09	6.31e+08	-2.15e+09	-8.56e+08	1.75e+09
16	make_5	Float32DType	314 (0.3%)	-1.98e+09	2.89e+08	-2.15e+09	-2.00e+09	7.58e+08
17	make_6	Float32DType	264 (0.2%)	-1.30e+09	3.18e+08	-2.14e+09	-1.15e+09	7.29e+08
18	make_7	Float32DType	323 (0.3%)	-1.71e+09	6.09e+08	-2.15e+09	-1.87e+09	1.20e+09
19	make_8	Float32DType	307 (0.3%)	-1.63e+09	2.74e+08	-2.15e+09	-1.52e+09	1.61e+09
20	model_0	Float32DType	429 (0.4%)	-1.92e+09	2.97e+08	-2.15e+09	-2.07e+09	0.00
21	model_1	Float32DType	309 (0.3%)	-2.07e+09	2.47e+08	-2.15e+09	-2.14e+09	0.00
22	model_2	Float32DType	309 (0.3%)	-2.06e+09	2.32e+08	-2.15e+09	-2.12e+09	4.22e+07
23	model_3	Float32DType	311 (0.3%)	-2.03e+09	2.36e+08	-2.15e+09	-2.10e+09	0.00
24	model_4	Float32DType	386 (0.4%)	-2.00e+09	2.32e+08	-2.15e+09	-1.99e+09	0.00
25	model_5	Float32DType	301 (0.3%)	-2.08e+09	2.29e+08	-2.15e+09	-2.10e+09	8.95e+08
26	model_6	Float32DType	296 (0.3%)	-1.85e+09	4.02e+08	-2.15e+09	-2.08e+09	0.00
27	model_7	Float32DType	329 (0.3%)	-2.00e+09	2.39e+08	-2.15e+09	-2.09e+09	0.00
28	model_8	Float32DType	385 (0.4%)	-1.96e+09	2.66e+08	-2.15e+09	-2.07e+09	0.00
29	goods_code_0	Float32DType	247 (0.2%)	-1.94e+09	1.69e+08	-2.15e+09	-1.95e+09	-2.78e+08
30	goods_code_1	Float32DType	249 (0.2%)	-1.89e+09	2.08e+08	-2.15e+09	-1.93e+09	-1.39e+08
31	goods_code_2	Float32DType	264 (0.2%)	-1.88e+09	2.56e+08	-2.15e+09	-1.92e+09	-2.86e+08
32	goods_code_3	Float32DType	199 (0.2%)	-1.99e+09	2.02e+08	-2.15e+09	-2.10e+09	-1.09e+08
33	goods_code_4	Float32DType	259 (0.2%)	-1.95e+09	2.30e+08	-2.14e+09	-2.05e+09	-9.31e+08
34	goods_code_5	Float32DType	270 (0.2%)	-1.97e+09	2.05e+08	-2.13e+09	-2.05e+09	-3.79e+08
35	goods_code_6	Float32DType	282 (0.3%)	-1.91e+09	2.02e+08	-2.15e+09	-1.97e+09	1.05e+09
36	goods_code_7	Float32DType	295 (0.3%)	-1.89e+09	1.91e+08	-2.15e+09	-1.88e+09	-3.88e+08
37	goods_code_8	Float32DType	228 (0.2%)	-1.90e+09	2.39e+08	-2.14e+09	-1.93e+09	-3.42e+08
38	Nbr_of_prod_purchas	Float32DType	19 (< 0.1%)	1.05	0.426	1.00	1.00	40.0
39	total_price	Float32DType	1454 (1.3%)	704.	882.	0.00	519.	7.13e+04

Please enable javascript

The skrub table reports need javascript to display correctly. If you are displaying a report in a Jupyter notebook and you see this message, you may need to re-execute the cell or to trust the notebook (button on the top right or "File > Trust notebook").

10: Apply TableVectorizer

This step used:

This step was used by:

Where was this step created?

Estimator fitted in this step:

Output of this step

basket_ID

item_0

item_1

item_2

item_3

item_4

item_5

item_6

item_7

item_8

cash_price

make_0

make_1

make_2

make_3

make_4

make_5

make_6

make_7

make_8

model_0

model_1

model_2

model_3

model_4

model_5

model_6

model_7

model_8

goods_code_0

goods_code_1

goods_code_2

goods_code_3

goods_code_4

goods_code_5

goods_code_6

goods_code_7

goods_code_8

Nbr_of_prod_purchas

total_price

Please enable javascript