Skip to content

Commit 68f8416

Browse files
author
Soledad Galli
committed
re-run ch2 after TR comments, no major changes
1 parent c1c56a3 commit 68f8416

11 files changed

+174
-110
lines changed

‎ch02-missing-data-imputation/Recipe-01-Removing-observations-with-missing-data.ipynb

+5-5
Original file line numberDiff line numberDiff line change
@@ -67,7 +67,7 @@
6767
" </thead>\n",
6868
" <tbody>\n",
6969
" <tr>\n",
70-
" <th>0</th>\n",
70+
" <td>0</td>\n",
7171
" <td>b</td>\n",
7272
" <td>30.83</td>\n",
7373
" <td>0.000</td>\n",
@@ -86,7 +86,7 @@
8686
" <td>1</td>\n",
8787
" </tr>\n",
8888
" <tr>\n",
89-
" <th>1</th>\n",
89+
" <td>1</td>\n",
9090
" <td>a</td>\n",
9191
" <td>58.67</td>\n",
9292
" <td>4.460</td>\n",
@@ -105,7 +105,7 @@
105105
" <td>1</td>\n",
106106
" </tr>\n",
107107
" <tr>\n",
108-
" <th>2</th>\n",
108+
" <td>2</td>\n",
109109
" <td>a</td>\n",
110110
" <td>24.50</td>\n",
111111
" <td>NaN</td>\n",
@@ -124,7 +124,7 @@
124124
" <td>1</td>\n",
125125
" </tr>\n",
126126
" <tr>\n",
127-
" <th>3</th>\n",
127+
" <td>3</td>\n",
128128
" <td>b</td>\n",
129129
" <td>27.83</td>\n",
130130
" <td>1.540</td>\n",
@@ -143,7 +143,7 @@
143143
" <td>1</td>\n",
144144
" </tr>\n",
145145
" <tr>\n",
146-
" <th>4</th>\n",
146+
" <td>4</td>\n",
147147
" <td>b</td>\n",
148148
" <td>20.17</td>\n",
149149
" <td>5.625</td>\n",

‎ch02-missing-data-imputation/Recipe-02-Performing-mean-or-median-imputation.ipynb

+16-7
Original file line numberDiff line numberDiff line change
@@ -75,7 +75,7 @@
7575
" </thead>\n",
7676
" <tbody>\n",
7777
" <tr>\n",
78-
" <th>0</th>\n",
78+
" <td>0</td>\n",
7979
" <td>b</td>\n",
8080
" <td>30.83</td>\n",
8181
" <td>0.000</td>\n",
@@ -94,7 +94,7 @@
9494
" <td>1</td>\n",
9595
" </tr>\n",
9696
" <tr>\n",
97-
" <th>1</th>\n",
97+
" <td>1</td>\n",
9898
" <td>a</td>\n",
9999
" <td>58.67</td>\n",
100100
" <td>4.460</td>\n",
@@ -113,7 +113,7 @@
113113
" <td>1</td>\n",
114114
" </tr>\n",
115115
" <tr>\n",
116-
" <th>2</th>\n",
116+
" <td>2</td>\n",
117117
" <td>a</td>\n",
118118
" <td>24.50</td>\n",
119119
" <td>NaN</td>\n",
@@ -132,7 +132,7 @@
132132
" <td>1</td>\n",
133133
" </tr>\n",
134134
" <tr>\n",
135-
" <th>3</th>\n",
135+
" <td>3</td>\n",
136136
" <td>b</td>\n",
137137
" <td>27.83</td>\n",
138138
" <td>1.540</td>\n",
@@ -151,7 +151,7 @@
151151
" <td>1</td>\n",
152152
" </tr>\n",
153153
" <tr>\n",
154-
" <th>4</th>\n",
154+
" <td>4</td>\n",
155155
" <td>b</td>\n",
156156
" <td>20.17</td>\n",
157157
" <td>5.625</td>\n",
@@ -399,7 +399,7 @@
399399
"cell_type": "markdown",
400400
"metadata": {},
401401
"source": [
402-
"## Mean / Median imputation with Feature Engine"
402+
"## Mean / Median imputation with Feature-engine"
403403
]
404404
},
405405
{
@@ -465,7 +465,16 @@
465465
"cell_type": "code",
466466
"execution_count": 14,
467467
"metadata": {},
468-
"outputs": [],
468+
"outputs": [
469+
{
470+
"name": "stderr",
471+
"output_type": "stream",
472+
"text": [
473+
"C:\\Users\\Sole\\Anaconda3\\envs\\feml\\lib\\site-packages\\sklearn\\utils\\validation.py:933: FutureWarning: Passing attributes to check_is_fitted is deprecated and will be removed in 0.23. The attributes argument is ignored.\n",
474+
" \"argument is ignored.\", FutureWarning)\n"
475+
]
476+
}
477+
],
469478
"source": [
470479
"# transform the data\n",
471480
"X_train = median_imputer.transform(X_train)\n",

‎ch02-missing-data-imputation/Recipe-03-Implementing-mode-or-frequent-category-imputation.ipynb

+16-7
Original file line numberDiff line numberDiff line change
@@ -75,7 +75,7 @@
7575
" </thead>\n",
7676
" <tbody>\n",
7777
" <tr>\n",
78-
" <th>0</th>\n",
78+
" <td>0</td>\n",
7979
" <td>b</td>\n",
8080
" <td>30.83</td>\n",
8181
" <td>0.000</td>\n",
@@ -94,7 +94,7 @@
9494
" <td>1</td>\n",
9595
" </tr>\n",
9696
" <tr>\n",
97-
" <th>1</th>\n",
97+
" <td>1</td>\n",
9898
" <td>a</td>\n",
9999
" <td>58.67</td>\n",
100100
" <td>4.460</td>\n",
@@ -113,7 +113,7 @@
113113
" <td>1</td>\n",
114114
" </tr>\n",
115115
" <tr>\n",
116-
" <th>2</th>\n",
116+
" <td>2</td>\n",
117117
" <td>a</td>\n",
118118
" <td>24.50</td>\n",
119119
" <td>NaN</td>\n",
@@ -132,7 +132,7 @@
132132
" <td>1</td>\n",
133133
" </tr>\n",
134134
" <tr>\n",
135-
" <th>3</th>\n",
135+
" <td>3</td>\n",
136136
" <td>b</td>\n",
137137
" <td>27.83</td>\n",
138138
" <td>1.540</td>\n",
@@ -151,7 +151,7 @@
151151
" <td>1</td>\n",
152152
" </tr>\n",
153153
" <tr>\n",
154-
" <th>4</th>\n",
154+
" <td>4</td>\n",
155155
" <td>b</td>\n",
156156
" <td>20.17</td>\n",
157157
" <td>5.625</td>\n",
@@ -392,7 +392,7 @@
392392
"cell_type": "markdown",
393393
"metadata": {},
394394
"source": [
395-
"## Frequent category imputation with feature engine"
395+
"## Frequent category imputation with Feature-engine"
396396
]
397397
},
398398
{
@@ -455,7 +455,16 @@
455455
"cell_type": "code",
456456
"execution_count": 14,
457457
"metadata": {},
458-
"outputs": [],
458+
"outputs": [
459+
{
460+
"name": "stderr",
461+
"output_type": "stream",
462+
"text": [
463+
"C:\\Users\\Sole\\Anaconda3\\envs\\feml\\lib\\site-packages\\sklearn\\utils\\validation.py:933: FutureWarning: Passing attributes to check_is_fitted is deprecated and will be removed in 0.23. The attributes argument is ignored.\n",
464+
" \"argument is ignored.\", FutureWarning)\n"
465+
]
466+
}
467+
],
459468
"source": [
460469
"# transform the data\n",
461470
"X_train = mode_imputer.transform(X_train)\n",

‎ch02-missing-data-imputation/Recipe-04-Replacing-missing-values-by-an-arbitrary-number.ipynb

+15-6
Original file line numberDiff line numberDiff line change
@@ -73,7 +73,7 @@
7373
" </thead>\n",
7474
" <tbody>\n",
7575
" <tr>\n",
76-
" <th>0</th>\n",
76+
" <td>0</td>\n",
7777
" <td>b</td>\n",
7878
" <td>30.83</td>\n",
7979
" <td>0.000</td>\n",
@@ -92,7 +92,7 @@
9292
" <td>1</td>\n",
9393
" </tr>\n",
9494
" <tr>\n",
95-
" <th>1</th>\n",
95+
" <td>1</td>\n",
9696
" <td>a</td>\n",
9797
" <td>58.67</td>\n",
9898
" <td>4.460</td>\n",
@@ -111,7 +111,7 @@
111111
" <td>1</td>\n",
112112
" </tr>\n",
113113
" <tr>\n",
114-
" <th>2</th>\n",
114+
" <td>2</td>\n",
115115
" <td>a</td>\n",
116116
" <td>24.50</td>\n",
117117
" <td>NaN</td>\n",
@@ -130,7 +130,7 @@
130130
" <td>1</td>\n",
131131
" </tr>\n",
132132
" <tr>\n",
133-
" <th>3</th>\n",
133+
" <td>3</td>\n",
134134
" <td>b</td>\n",
135135
" <td>27.83</td>\n",
136136
" <td>1.540</td>\n",
@@ -149,7 +149,7 @@
149149
" <td>1</td>\n",
150150
" </tr>\n",
151151
" <tr>\n",
152-
" <th>4</th>\n",
152+
" <td>4</td>\n",
153153
" <td>b</td>\n",
154154
" <td>20.17</td>\n",
155155
" <td>5.625</td>\n",
@@ -480,7 +480,16 @@
480480
"cell_type": "code",
481481
"execution_count": 15,
482482
"metadata": {},
483-
"outputs": [],
483+
"outputs": [
484+
{
485+
"name": "stderr",
486+
"output_type": "stream",
487+
"text": [
488+
"C:\\Users\\Sole\\Anaconda3\\envs\\feml\\lib\\site-packages\\sklearn\\utils\\validation.py:933: FutureWarning: Passing attributes to check_is_fitted is deprecated and will be removed in 0.23. The attributes argument is ignored.\n",
489+
" \"argument is ignored.\", FutureWarning)\n"
490+
]
491+
}
492+
],
484493
"source": [
485494
"# transform the data\n",
486495
"X_train = imputer.transform(X_train)\n",

‎ch02-missing-data-imputation/Recipe-05-Capturing-missing-values-in-a-bespoke-category.ipynb

+15-6
Original file line numberDiff line numberDiff line change
@@ -73,7 +73,7 @@
7373
" </thead>\n",
7474
" <tbody>\n",
7575
" <tr>\n",
76-
" <th>0</th>\n",
76+
" <td>0</td>\n",
7777
" <td>b</td>\n",
7878
" <td>30.83</td>\n",
7979
" <td>0.000</td>\n",
@@ -92,7 +92,7 @@
9292
" <td>1</td>\n",
9393
" </tr>\n",
9494
" <tr>\n",
95-
" <th>1</th>\n",
95+
" <td>1</td>\n",
9696
" <td>a</td>\n",
9797
" <td>58.67</td>\n",
9898
" <td>4.460</td>\n",
@@ -111,7 +111,7 @@
111111
" <td>1</td>\n",
112112
" </tr>\n",
113113
" <tr>\n",
114-
" <th>2</th>\n",
114+
" <td>2</td>\n",
115115
" <td>a</td>\n",
116116
" <td>24.50</td>\n",
117117
" <td>NaN</td>\n",
@@ -130,7 +130,7 @@
130130
" <td>1</td>\n",
131131
" </tr>\n",
132132
" <tr>\n",
133-
" <th>3</th>\n",
133+
" <td>3</td>\n",
134134
" <td>b</td>\n",
135135
" <td>27.83</td>\n",
136136
" <td>1.540</td>\n",
@@ -149,7 +149,7 @@
149149
" <td>1</td>\n",
150150
" </tr>\n",
151151
" <tr>\n",
152-
" <th>4</th>\n",
152+
" <td>4</td>\n",
153153
" <td>b</td>\n",
154154
" <td>20.17</td>\n",
155155
" <td>5.625</td>\n",
@@ -426,7 +426,16 @@
426426
"cell_type": "code",
427427
"execution_count": 13,
428428
"metadata": {},
429-
"outputs": [],
429+
"outputs": [
430+
{
431+
"name": "stderr",
432+
"output_type": "stream",
433+
"text": [
434+
"C:\\Users\\Sole\\Anaconda3\\envs\\feml\\lib\\site-packages\\sklearn\\utils\\validation.py:933: FutureWarning: Passing attributes to check_is_fitted is deprecated and will be removed in 0.23. The attributes argument is ignored.\n",
435+
" \"argument is ignored.\", FutureWarning)\n"
436+
]
437+
}
438+
],
430439
"source": [
431440
"# transform the data\n",
432441
"X_train = imputer.transform(X_train)\n",

‎ch02-missing-data-imputation/Recipe-06-Replacing-missing-values-by-a-value-at-the-end-of-the-distribution.ipynb

+15-6
Original file line numberDiff line numberDiff line change
@@ -77,7 +77,7 @@
7777
" </thead>\n",
7878
" <tbody>\n",
7979
" <tr>\n",
80-
" <th>0</th>\n",
80+
" <td>0</td>\n",
8181
" <td>b</td>\n",
8282
" <td>30.83</td>\n",
8383
" <td>0.000</td>\n",
@@ -96,7 +96,7 @@
9696
" <td>1</td>\n",
9797
" </tr>\n",
9898
" <tr>\n",
99-
" <th>1</th>\n",
99+
" <td>1</td>\n",
100100
" <td>a</td>\n",
101101
" <td>58.67</td>\n",
102102
" <td>4.460</td>\n",
@@ -115,7 +115,7 @@
115115
" <td>1</td>\n",
116116
" </tr>\n",
117117
" <tr>\n",
118-
" <th>2</th>\n",
118+
" <td>2</td>\n",
119119
" <td>a</td>\n",
120120
" <td>24.50</td>\n",
121121
" <td>NaN</td>\n",
@@ -134,7 +134,7 @@
134134
" <td>1</td>\n",
135135
" </tr>\n",
136136
" <tr>\n",
137-
" <th>3</th>\n",
137+
" <td>3</td>\n",
138138
" <td>b</td>\n",
139139
" <td>27.83</td>\n",
140140
" <td>1.540</td>\n",
@@ -153,7 +153,7 @@
153153
" <td>1</td>\n",
154154
" </tr>\n",
155155
" <tr>\n",
156-
" <th>4</th>\n",
156+
" <td>4</td>\n",
157157
" <td>b</td>\n",
158158
" <td>20.17</td>\n",
159159
" <td>5.625</td>\n",
@@ -375,7 +375,16 @@
375375
"cell_type": "code",
376376
"execution_count": 10,
377377
"metadata": {},
378-
"outputs": [],
378+
"outputs": [
379+
{
380+
"name": "stderr",
381+
"output_type": "stream",
382+
"text": [
383+
"C:\\Users\\Sole\\Anaconda3\\envs\\feml\\lib\\site-packages\\sklearn\\utils\\validation.py:933: FutureWarning: Passing attributes to check_is_fitted is deprecated and will be removed in 0.23. The attributes argument is ignored.\n",
384+
" \"argument is ignored.\", FutureWarning)\n"
385+
]
386+
}
387+
],
379388
"source": [
380389
"# transform the data\n",
381390
"X_train = imputer.transform(X_train)\n",

0 commit comments

Comments
 (0)