Skip to content

Commit 1e42e2f

Browse files
andrey-khropovandrey-khropov
committed
create_cd fix: dict keys in feature_names are column indices. Add tests.. Fixes #2211.
1 parent 1409fb3 commit 1e42e2f

13 files changed

+13
-13
lines changed

‎classification/classification_tutorial.ipynb

+1-1
Original file line numberDiff line numberDiff line change
@@ -371,7 +371,7 @@
371371
"for column, name in enumerate(train_df):\n",
372372
" if column == 0:\n",
373373
" continue\n",
374-
" feature_names[column - 1] = name\n",
374+
" feature_names[column] = name\n",
375375
" \n",
376376
"create_cd(\n",
377377
" label=0, \n",

‎events/2019_10_30_odsc_west.ipynb

+1-1
Original file line numberDiff line numberDiff line change
@@ -199,7 +199,7 @@
199199
"outputs": [],
200200
"source": [
201201
"from catboost.utils import create_cd\n",
202-
"feature_names = dict(list(enumerate(train_df.keys()[1:])))\n",
202+
"feature_names = dict(list(enumerate(train_df.keys()))[1:])\n",
203203
" \n",
204204
"create_cd(\n",
205205
" label=0,\n",

‎events/2019_odsc_east/odsc_east_2019.ipynb

+1-1
Original file line numberDiff line numberDiff line change
@@ -434,7 +434,7 @@
434434
"outputs": [],
435435
"source": [
436436
"from catboost.utils import create_cd\n",
437-
"feature_names = dict(list(enumerate(train_df.keys()[1:])))\n",
437+
"feature_names = dict(list(enumerate(train_df.keys()))[1:])\n",
438438
" \n",
439439
"create_cd(\n",
440440
" label=0,\n",

‎events/2020_06_04_catboost_tutorial/catboost_features.ipynb

+1-1
Original file line numberDiff line numberDiff line change
@@ -148,7 +148,7 @@
148148
"outputs": [],
149149
"source": [
150150
"from catboost.utils import create_cd\n",
151-
"feature_names = dict(map(lambda i: (i, 'Feature ' + str(i)), range(train_df.shape[1] - 2)))\n",
151+
"feature_names = dict(map(lambda i: (i + 2, 'Feature ' + str(i)), range(train_df.shape[1])))\n",
152152
" \n",
153153
"create_cd(\n",
154154
" label=0,\n",

‎events/2020_odsc_west/text_features.ipynb

+1-1
Original file line numberDiff line numberDiff line change
@@ -187,7 +187,7 @@
187187
"outputs": [],
188188
"source": [
189189
"from catboost.utils import create_cd\n",
190-
"feature_names = dict(map(lambda i: (i, 'Feature ' + str(i)), range(train_df.shape[1] - 2)))\n",
190+
"feature_names = dict(map(lambda i: (i + 2, 'Feature ' + str(i)), range(train_df.shape[1])))\n",
191191
" \n",
192192
"create_cd(\n",
193193
" label=0,\n",

‎events/datastart_moscow_apr_27_2019.ipynb

+1-1
Original file line numberDiff line numberDiff line change
@@ -338,7 +338,7 @@
338338
"outputs": [],
339339
"source": [
340340
"from catboost.utils import create_cd\n",
341-
"feature_names = dict(list(enumerate(train_df.keys()[1:])))\n",
341+
"feature_names = dict(list(enumerate(train_df.keys()))[1:])\n",
342342
" \n",
343343
"create_cd(\n",
344344
" label=0,\n",

‎events/intel_hands_on_moscow_oct_11_2019.ipynb

+1-1
Original file line numberDiff line numberDiff line change
@@ -154,7 +154,7 @@
154154
"outputs": [],
155155
"source": [
156156
"from catboost.utils import create_cd\n",
157-
"feature_names = dict(list(enumerate(train_df.keys()[1:])))\n",
157+
"feature_names = dict(list(enumerate(train_df.keys()))[1:])\n",
158158
" \n",
159159
"create_cd(\n",
160160
" label=0,\n",

‎events/pydata_la_oct_21_2018.ipynb

+1-1
Original file line numberDiff line numberDiff line change
@@ -450,7 +450,7 @@
450450
"for column, name in enumerate(train_df):\n",
451451
" if column == 0:\n",
452452
" continue\n",
453-
" feature_names[column - 1] = name\n",
453+
" feature_names[column] = name\n",
454454
" \n",
455455
"create_cd(\n",
456456
" label=0, \n",

‎events/pydata_moscow_oct_13_2018.ipynb

+1-1
Original file line numberDiff line numberDiff line change
@@ -371,7 +371,7 @@
371371
"for column, name in enumerate(train_df):\n",
372372
" if column == 0:\n",
373373
" continue\n",
374-
" feature_names[column - 1] = name\n",
374+
" feature_names[column] = name\n",
375375
" \n",
376376
"create_cd(\n",
377377
" label=0, \n",

‎events/pydata_nyc_oct_19_2018.ipynb

+1-1
Original file line numberDiff line numberDiff line change
@@ -450,7 +450,7 @@
450450
"for column, name in enumerate(train_df):\n",
451451
" if column == 0:\n",
452452
" continue\n",
453-
" feature_names[column - 1] = name\n",
453+
" feature_names[column] = name\n",
454454
" \n",
455455
"create_cd(\n",
456456
" label=0, \n",

‎feature_selection/eval_tutorial.ipynb

+1-1
Original file line numberDiff line numberDiff line change
@@ -152,7 +152,7 @@
152152
"for column, name in enumerate(train_df):\n",
153153
" if column == 0:\n",
154154
" continue\n",
155-
" feature_names[column - 1] = name\n",
155+
" feature_names[column] = name\n",
156156
" \n",
157157
"create_cd(\n",
158158
" label=0, \n",

‎python_tutorial_with_tasks.ipynb

+1-1
Original file line numberDiff line numberDiff line change
@@ -282,7 +282,7 @@
282282
"outputs": [],
283283
"source": [
284284
"from catboost.utils import create_cd\n",
285-
"feature_names = dict(list(enumerate(train_df.keys()[1:])))\n",
285+
"feature_names = dict(list(enumerate(train_df.keys()))[1:])\n",
286286
" \n",
287287
"create_cd(\n",
288288
" label=0,\n",

‎ru/kaggle_amazon_tutorial_ru.ipynb

+1-1
Original file line numberDiff line numberDiff line change
@@ -238,7 +238,7 @@
238238
"for column, name in enumerate(train_df):\n",
239239
" if column == 0:\n",
240240
" continue\n",
241-
" feature_names[column - 1] = name\n",
241+
" feature_names[column] = name\n",
242242
" \n",
243243
"create_cd(\n",
244244
" label=0, \n",

0 commit comments

Comments
 (0)