noshot 4.0.0__py3-none-any.whl → 5.0.0__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- noshot/data/ML TS XAI/XAI/Q1.ipynb +535 -0
- noshot/data/ML TS XAI/XAI/Q2.ipynb +38129 -0
- noshot/data/ML TS XAI/XAI/Q3.ipynb +1340 -0
- noshot/data/ML TS XAI/XAI/Q4.ipynb +246 -0
- noshot/data/ML TS XAI/XAI/Q5.ipynb +2450 -0
- {noshot-4.0.0.dist-info → noshot-5.0.0.dist-info}/METADATA +1 -1
- noshot-5.0.0.dist-info/RECORD +14 -0
- noshot/data/ML TS XAI/ML/ML Lab CIA 2 (I Found Only This Check)/Copy_of_Pistachio_csv.ipynb +0 -269
- noshot/data/ML TS XAI/ML/ML Lab CIA 2 (I Found Only This Check)/weatherAUS.ipynb +0 -155
- noshot/data/ML TS XAI/ML/Main/1. EDA-PCA (Balance Scale Dataset).ipynb +0 -139
- noshot/data/ML TS XAI/ML/Main/1. EDA-PCA (Rice Dataset).ipynb +0 -181
- noshot/data/ML TS XAI/ML/Main/10. HMM Veterbi.ipynb +0 -228
- noshot/data/ML TS XAI/ML/Main/2. KNN (Balance Scale Dataset).ipynb +0 -117
- noshot/data/ML TS XAI/ML/Main/2. KNN (Iris Dataset).ipynb +0 -165
- noshot/data/ML TS XAI/ML/Main/2. KNN (Sobar-72 Dataset).ipynb +0 -251
- noshot/data/ML TS XAI/ML/Main/3. LDA (Balance Scale Dataset).ipynb +0 -78
- noshot/data/ML TS XAI/ML/Main/3. LDA (NPHA Doctor Visits Dataset).ipynb +0 -114
- noshot/data/ML TS XAI/ML/Main/4. Linear Regression (Machine Dataset).ipynb +0 -115
- noshot/data/ML TS XAI/ML/Main/4. Linear Regression (Real Estate Dataset).ipynb +0 -159
- noshot/data/ML TS XAI/ML/Main/5. Logistic Regression (Magic04 Dataset).ipynb +0 -200
- noshot/data/ML TS XAI/ML/Main/5. Logistic Regression (Wine Dataset).ipynb +0 -112
- noshot/data/ML TS XAI/ML/Main/6. Naive Bayes Classifier (Agaricus Lepiota Dataset).ipynb +0 -153
- noshot/data/ML TS XAI/ML/Main/6. Naive Bayes Classifier (Wine Dataset).ipynb +0 -89
- noshot/data/ML TS XAI/ML/Main/7. SVM (Rice Dataset).ipynb +0 -208
- noshot/data/ML TS XAI/ML/Main/8. FeedForward NN (Sobar72 Dataset).ipynb +0 -260
- noshot/data/ML TS XAI/ML/Main/9. CNN (Cifar10 Dataset).ipynb +0 -238
- noshot/data/ML TS XAI/ML/Main/data/agaricus-lepiota.data +0 -8124
- noshot/data/ML TS XAI/ML/Main/data/balance-scale.txt +0 -625
- noshot/data/ML TS XAI/ML/Main/data/doctor-visits.csv +0 -715
- noshot/data/ML TS XAI/ML/Main/data/iris.csv +0 -151
- noshot/data/ML TS XAI/ML/Main/data/machine-data.csv +0 -210
- noshot/data/ML TS XAI/ML/Main/data/magic04.data +0 -19020
- noshot/data/ML TS XAI/ML/Main/data/real-estate.xlsx +0 -0
- noshot/data/ML TS XAI/ML/Main/data/rice.arff +0 -3826
- noshot/data/ML TS XAI/ML/Main/data/sobar-72.csv +0 -73
- noshot/data/ML TS XAI/ML/Main/data/wine-dataset.csv +0 -179
- noshot/data/ML TS XAI/ML/Other Codes.ipynb +0 -158
- noshot/data/ML TS XAI/ML/Rolls Royce AllinOne.ipynb +0 -691
- noshot-4.0.0.dist-info/RECORD +0 -40
- {noshot-4.0.0.dist-info → noshot-5.0.0.dist-info}/WHEEL +0 -0
- {noshot-4.0.0.dist-info → noshot-5.0.0.dist-info}/licenses/LICENSE.txt +0 -0
- {noshot-4.0.0.dist-info → noshot-5.0.0.dist-info}/top_level.txt +0 -0
|
@@ -0,0 +1,1340 @@
|
|
|
1
|
+
{
|
|
2
|
+
"cells": [
|
|
3
|
+
{
|
|
4
|
+
"cell_type": "markdown",
|
|
5
|
+
"metadata": {
|
|
6
|
+
"id": "0cPxrLdh65Uq"
|
|
7
|
+
},
|
|
8
|
+
"source": [
|
|
9
|
+
"**Perform Partial dependence plot (PDP)**"
|
|
10
|
+
]
|
|
11
|
+
},
|
|
12
|
+
{
|
|
13
|
+
"cell_type": "code",
|
|
14
|
+
"execution_count": 1,
|
|
15
|
+
"metadata": {
|
|
16
|
+
"id": "kUCRkjNG6mLx"
|
|
17
|
+
},
|
|
18
|
+
"outputs": [],
|
|
19
|
+
"source": [
|
|
20
|
+
"from sklearn.datasets import fetch_california_housing\n",
|
|
21
|
+
"from sklearn.ensemble import RandomForestRegressor\n",
|
|
22
|
+
"from sklearn.inspection import PartialDependenceDisplay\n",
|
|
23
|
+
"from sklearn.model_selection import train_test_split\n",
|
|
24
|
+
"import matplotlib.pyplot as plt\n",
|
|
25
|
+
"import pandas as pd\n",
|
|
26
|
+
"import numpy as np"
|
|
27
|
+
]
|
|
28
|
+
},
|
|
29
|
+
{
|
|
30
|
+
"cell_type": "code",
|
|
31
|
+
"execution_count": 2,
|
|
32
|
+
"metadata": {
|
|
33
|
+
"colab": {
|
|
34
|
+
"base_uri": "https://localhost:8080/",
|
|
35
|
+
"height": 223
|
|
36
|
+
},
|
|
37
|
+
"id": "Q7p6o9_z6qhJ",
|
|
38
|
+
"outputId": "c04efdf3-948e-42e0-a31c-d6fee03a6d7f",
|
|
39
|
+
"scrolled": true
|
|
40
|
+
},
|
|
41
|
+
"outputs": [
|
|
42
|
+
{
|
|
43
|
+
"data": {
|
|
44
|
+
"text/html": [
|
|
45
|
+
"<div>\n",
|
|
46
|
+
"<style scoped>\n",
|
|
47
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
48
|
+
" vertical-align: middle;\n",
|
|
49
|
+
" }\n",
|
|
50
|
+
"\n",
|
|
51
|
+
" .dataframe tbody tr th {\n",
|
|
52
|
+
" vertical-align: top;\n",
|
|
53
|
+
" }\n",
|
|
54
|
+
"\n",
|
|
55
|
+
" .dataframe thead th {\n",
|
|
56
|
+
" text-align: right;\n",
|
|
57
|
+
" }\n",
|
|
58
|
+
"</style>\n",
|
|
59
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
60
|
+
" <thead>\n",
|
|
61
|
+
" <tr style=\"text-align: right;\">\n",
|
|
62
|
+
" <th></th>\n",
|
|
63
|
+
" <th>MedInc</th>\n",
|
|
64
|
+
" <th>HouseAge</th>\n",
|
|
65
|
+
" <th>AveRooms</th>\n",
|
|
66
|
+
" <th>AveBedrms</th>\n",
|
|
67
|
+
" <th>Population</th>\n",
|
|
68
|
+
" <th>AveOccup</th>\n",
|
|
69
|
+
" <th>Latitude</th>\n",
|
|
70
|
+
" <th>Longitude</th>\n",
|
|
71
|
+
" <th>target</th>\n",
|
|
72
|
+
" </tr>\n",
|
|
73
|
+
" </thead>\n",
|
|
74
|
+
" <tbody>\n",
|
|
75
|
+
" <tr>\n",
|
|
76
|
+
" <th>0</th>\n",
|
|
77
|
+
" <td>8.3252</td>\n",
|
|
78
|
+
" <td>41.0</td>\n",
|
|
79
|
+
" <td>6.984127</td>\n",
|
|
80
|
+
" <td>1.023810</td>\n",
|
|
81
|
+
" <td>322.0</td>\n",
|
|
82
|
+
" <td>2.555556</td>\n",
|
|
83
|
+
" <td>37.88</td>\n",
|
|
84
|
+
" <td>-122.23</td>\n",
|
|
85
|
+
" <td>4.526</td>\n",
|
|
86
|
+
" </tr>\n",
|
|
87
|
+
" <tr>\n",
|
|
88
|
+
" <th>1</th>\n",
|
|
89
|
+
" <td>8.3014</td>\n",
|
|
90
|
+
" <td>21.0</td>\n",
|
|
91
|
+
" <td>6.238137</td>\n",
|
|
92
|
+
" <td>0.971880</td>\n",
|
|
93
|
+
" <td>2401.0</td>\n",
|
|
94
|
+
" <td>2.109842</td>\n",
|
|
95
|
+
" <td>37.86</td>\n",
|
|
96
|
+
" <td>-122.22</td>\n",
|
|
97
|
+
" <td>3.585</td>\n",
|
|
98
|
+
" </tr>\n",
|
|
99
|
+
" <tr>\n",
|
|
100
|
+
" <th>2</th>\n",
|
|
101
|
+
" <td>7.2574</td>\n",
|
|
102
|
+
" <td>52.0</td>\n",
|
|
103
|
+
" <td>8.288136</td>\n",
|
|
104
|
+
" <td>1.073446</td>\n",
|
|
105
|
+
" <td>496.0</td>\n",
|
|
106
|
+
" <td>2.802260</td>\n",
|
|
107
|
+
" <td>37.85</td>\n",
|
|
108
|
+
" <td>-122.24</td>\n",
|
|
109
|
+
" <td>3.521</td>\n",
|
|
110
|
+
" </tr>\n",
|
|
111
|
+
" <tr>\n",
|
|
112
|
+
" <th>3</th>\n",
|
|
113
|
+
" <td>5.6431</td>\n",
|
|
114
|
+
" <td>52.0</td>\n",
|
|
115
|
+
" <td>5.817352</td>\n",
|
|
116
|
+
" <td>1.073059</td>\n",
|
|
117
|
+
" <td>558.0</td>\n",
|
|
118
|
+
" <td>2.547945</td>\n",
|
|
119
|
+
" <td>37.85</td>\n",
|
|
120
|
+
" <td>-122.25</td>\n",
|
|
121
|
+
" <td>3.413</td>\n",
|
|
122
|
+
" </tr>\n",
|
|
123
|
+
" <tr>\n",
|
|
124
|
+
" <th>4</th>\n",
|
|
125
|
+
" <td>3.8462</td>\n",
|
|
126
|
+
" <td>52.0</td>\n",
|
|
127
|
+
" <td>6.281853</td>\n",
|
|
128
|
+
" <td>1.081081</td>\n",
|
|
129
|
+
" <td>565.0</td>\n",
|
|
130
|
+
" <td>2.181467</td>\n",
|
|
131
|
+
" <td>37.85</td>\n",
|
|
132
|
+
" <td>-122.25</td>\n",
|
|
133
|
+
" <td>3.422</td>\n",
|
|
134
|
+
" </tr>\n",
|
|
135
|
+
" </tbody>\n",
|
|
136
|
+
"</table>\n",
|
|
137
|
+
"</div>"
|
|
138
|
+
],
|
|
139
|
+
"text/plain": [
|
|
140
|
+
" MedInc HouseAge AveRooms AveBedrms Population AveOccup Latitude \\\n",
|
|
141
|
+
"0 8.3252 41.0 6.984127 1.023810 322.0 2.555556 37.88 \n",
|
|
142
|
+
"1 8.3014 21.0 6.238137 0.971880 2401.0 2.109842 37.86 \n",
|
|
143
|
+
"2 7.2574 52.0 8.288136 1.073446 496.0 2.802260 37.85 \n",
|
|
144
|
+
"3 5.6431 52.0 5.817352 1.073059 558.0 2.547945 37.85 \n",
|
|
145
|
+
"4 3.8462 52.0 6.281853 1.081081 565.0 2.181467 37.85 \n",
|
|
146
|
+
"\n",
|
|
147
|
+
" Longitude target \n",
|
|
148
|
+
"0 -122.23 4.526 \n",
|
|
149
|
+
"1 -122.22 3.585 \n",
|
|
150
|
+
"2 -122.24 3.521 \n",
|
|
151
|
+
"3 -122.25 3.413 \n",
|
|
152
|
+
"4 -122.25 3.422 "
|
|
153
|
+
]
|
|
154
|
+
},
|
|
155
|
+
"execution_count": 2,
|
|
156
|
+
"metadata": {},
|
|
157
|
+
"output_type": "execute_result"
|
|
158
|
+
}
|
|
159
|
+
],
|
|
160
|
+
"source": [
|
|
161
|
+
"df=pd.read_csv('cali.csv')\n",
|
|
162
|
+
"df.head()"
|
|
163
|
+
]
|
|
164
|
+
},
|
|
165
|
+
{
|
|
166
|
+
"cell_type": "code",
|
|
167
|
+
"execution_count": 3,
|
|
168
|
+
"metadata": {},
|
|
169
|
+
"outputs": [],
|
|
170
|
+
"source": [
|
|
171
|
+
"X=df.drop(columns='target')\n",
|
|
172
|
+
"y=df['target']"
|
|
173
|
+
]
|
|
174
|
+
},
|
|
175
|
+
{
|
|
176
|
+
"cell_type": "code",
|
|
177
|
+
"execution_count": 4,
|
|
178
|
+
"metadata": {
|
|
179
|
+
"colab": {
|
|
180
|
+
"base_uri": "https://localhost:8080/",
|
|
181
|
+
"height": 80
|
|
182
|
+
},
|
|
183
|
+
"id": "auzRXSjU6tR8",
|
|
184
|
+
"outputId": "77452de0-80b8-495a-a3a5-b3a94e1bc17c"
|
|
185
|
+
},
|
|
186
|
+
"outputs": [
|
|
187
|
+
{
|
|
188
|
+
"data": {
|
|
189
|
+
"text/html": [
|
|
190
|
+
"<style>#sk-container-id-1 {\n",
|
|
191
|
+
" /* Definition of color scheme common for light and dark mode */\n",
|
|
192
|
+
" --sklearn-color-text: #000;\n",
|
|
193
|
+
" --sklearn-color-text-muted: #666;\n",
|
|
194
|
+
" --sklearn-color-line: gray;\n",
|
|
195
|
+
" /* Definition of color scheme for unfitted estimators */\n",
|
|
196
|
+
" --sklearn-color-unfitted-level-0: #fff5e6;\n",
|
|
197
|
+
" --sklearn-color-unfitted-level-1: #f6e4d2;\n",
|
|
198
|
+
" --sklearn-color-unfitted-level-2: #ffe0b3;\n",
|
|
199
|
+
" --sklearn-color-unfitted-level-3: chocolate;\n",
|
|
200
|
+
" /* Definition of color scheme for fitted estimators */\n",
|
|
201
|
+
" --sklearn-color-fitted-level-0: #f0f8ff;\n",
|
|
202
|
+
" --sklearn-color-fitted-level-1: #d4ebff;\n",
|
|
203
|
+
" --sklearn-color-fitted-level-2: #b3dbfd;\n",
|
|
204
|
+
" --sklearn-color-fitted-level-3: cornflowerblue;\n",
|
|
205
|
+
"\n",
|
|
206
|
+
" /* Specific color for light theme */\n",
|
|
207
|
+
" --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
|
|
208
|
+
" --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
|
|
209
|
+
" --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
|
|
210
|
+
" --sklearn-color-icon: #696969;\n",
|
|
211
|
+
"\n",
|
|
212
|
+
" @media (prefers-color-scheme: dark) {\n",
|
|
213
|
+
" /* Redefinition of color scheme for dark theme */\n",
|
|
214
|
+
" --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
|
|
215
|
+
" --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
|
|
216
|
+
" --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
|
|
217
|
+
" --sklearn-color-icon: #878787;\n",
|
|
218
|
+
" }\n",
|
|
219
|
+
"}\n",
|
|
220
|
+
"\n",
|
|
221
|
+
"#sk-container-id-1 {\n",
|
|
222
|
+
" color: var(--sklearn-color-text);\n",
|
|
223
|
+
"}\n",
|
|
224
|
+
"\n",
|
|
225
|
+
"#sk-container-id-1 pre {\n",
|
|
226
|
+
" padding: 0;\n",
|
|
227
|
+
"}\n",
|
|
228
|
+
"\n",
|
|
229
|
+
"#sk-container-id-1 input.sk-hidden--visually {\n",
|
|
230
|
+
" border: 0;\n",
|
|
231
|
+
" clip: rect(1px 1px 1px 1px);\n",
|
|
232
|
+
" clip: rect(1px, 1px, 1px, 1px);\n",
|
|
233
|
+
" height: 1px;\n",
|
|
234
|
+
" margin: -1px;\n",
|
|
235
|
+
" overflow: hidden;\n",
|
|
236
|
+
" padding: 0;\n",
|
|
237
|
+
" position: absolute;\n",
|
|
238
|
+
" width: 1px;\n",
|
|
239
|
+
"}\n",
|
|
240
|
+
"\n",
|
|
241
|
+
"#sk-container-id-1 div.sk-dashed-wrapped {\n",
|
|
242
|
+
" border: 1px dashed var(--sklearn-color-line);\n",
|
|
243
|
+
" margin: 0 0.4em 0.5em 0.4em;\n",
|
|
244
|
+
" box-sizing: border-box;\n",
|
|
245
|
+
" padding-bottom: 0.4em;\n",
|
|
246
|
+
" background-color: var(--sklearn-color-background);\n",
|
|
247
|
+
"}\n",
|
|
248
|
+
"\n",
|
|
249
|
+
"#sk-container-id-1 div.sk-container {\n",
|
|
250
|
+
" /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
|
|
251
|
+
" but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
|
|
252
|
+
" so we also need the `!important` here to be able to override the\n",
|
|
253
|
+
" default hidden behavior on the sphinx rendered scikit-learn.org.\n",
|
|
254
|
+
" See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
|
|
255
|
+
" display: inline-block !important;\n",
|
|
256
|
+
" position: relative;\n",
|
|
257
|
+
"}\n",
|
|
258
|
+
"\n",
|
|
259
|
+
"#sk-container-id-1 div.sk-text-repr-fallback {\n",
|
|
260
|
+
" display: none;\n",
|
|
261
|
+
"}\n",
|
|
262
|
+
"\n",
|
|
263
|
+
"div.sk-parallel-item,\n",
|
|
264
|
+
"div.sk-serial,\n",
|
|
265
|
+
"div.sk-item {\n",
|
|
266
|
+
" /* draw centered vertical line to link estimators */\n",
|
|
267
|
+
" background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
|
|
268
|
+
" background-size: 2px 100%;\n",
|
|
269
|
+
" background-repeat: no-repeat;\n",
|
|
270
|
+
" background-position: center center;\n",
|
|
271
|
+
"}\n",
|
|
272
|
+
"\n",
|
|
273
|
+
"/* Parallel-specific style estimator block */\n",
|
|
274
|
+
"\n",
|
|
275
|
+
"#sk-container-id-1 div.sk-parallel-item::after {\n",
|
|
276
|
+
" content: \"\";\n",
|
|
277
|
+
" width: 100%;\n",
|
|
278
|
+
" border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
|
|
279
|
+
" flex-grow: 1;\n",
|
|
280
|
+
"}\n",
|
|
281
|
+
"\n",
|
|
282
|
+
"#sk-container-id-1 div.sk-parallel {\n",
|
|
283
|
+
" display: flex;\n",
|
|
284
|
+
" align-items: stretch;\n",
|
|
285
|
+
" justify-content: center;\n",
|
|
286
|
+
" background-color: var(--sklearn-color-background);\n",
|
|
287
|
+
" position: relative;\n",
|
|
288
|
+
"}\n",
|
|
289
|
+
"\n",
|
|
290
|
+
"#sk-container-id-1 div.sk-parallel-item {\n",
|
|
291
|
+
" display: flex;\n",
|
|
292
|
+
" flex-direction: column;\n",
|
|
293
|
+
"}\n",
|
|
294
|
+
"\n",
|
|
295
|
+
"#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
|
|
296
|
+
" align-self: flex-end;\n",
|
|
297
|
+
" width: 50%;\n",
|
|
298
|
+
"}\n",
|
|
299
|
+
"\n",
|
|
300
|
+
"#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
|
|
301
|
+
" align-self: flex-start;\n",
|
|
302
|
+
" width: 50%;\n",
|
|
303
|
+
"}\n",
|
|
304
|
+
"\n",
|
|
305
|
+
"#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
|
|
306
|
+
" width: 0;\n",
|
|
307
|
+
"}\n",
|
|
308
|
+
"\n",
|
|
309
|
+
"/* Serial-specific style estimator block */\n",
|
|
310
|
+
"\n",
|
|
311
|
+
"#sk-container-id-1 div.sk-serial {\n",
|
|
312
|
+
" display: flex;\n",
|
|
313
|
+
" flex-direction: column;\n",
|
|
314
|
+
" align-items: center;\n",
|
|
315
|
+
" background-color: var(--sklearn-color-background);\n",
|
|
316
|
+
" padding-right: 1em;\n",
|
|
317
|
+
" padding-left: 1em;\n",
|
|
318
|
+
"}\n",
|
|
319
|
+
"\n",
|
|
320
|
+
"\n",
|
|
321
|
+
"/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
|
|
322
|
+
"clickable and can be expanded/collapsed.\n",
|
|
323
|
+
"- Pipeline and ColumnTransformer use this feature and define the default style\n",
|
|
324
|
+
"- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
|
|
325
|
+
"*/\n",
|
|
326
|
+
"\n",
|
|
327
|
+
"/* Pipeline and ColumnTransformer style (default) */\n",
|
|
328
|
+
"\n",
|
|
329
|
+
"#sk-container-id-1 div.sk-toggleable {\n",
|
|
330
|
+
" /* Default theme specific background. It is overwritten whether we have a\n",
|
|
331
|
+
" specific estimator or a Pipeline/ColumnTransformer */\n",
|
|
332
|
+
" background-color: var(--sklearn-color-background);\n",
|
|
333
|
+
"}\n",
|
|
334
|
+
"\n",
|
|
335
|
+
"/* Toggleable label */\n",
|
|
336
|
+
"#sk-container-id-1 label.sk-toggleable__label {\n",
|
|
337
|
+
" cursor: pointer;\n",
|
|
338
|
+
" display: flex;\n",
|
|
339
|
+
" width: 100%;\n",
|
|
340
|
+
" margin-bottom: 0;\n",
|
|
341
|
+
" padding: 0.5em;\n",
|
|
342
|
+
" box-sizing: border-box;\n",
|
|
343
|
+
" text-align: center;\n",
|
|
344
|
+
" align-items: start;\n",
|
|
345
|
+
" justify-content: space-between;\n",
|
|
346
|
+
" gap: 0.5em;\n",
|
|
347
|
+
"}\n",
|
|
348
|
+
"\n",
|
|
349
|
+
"#sk-container-id-1 label.sk-toggleable__label .caption {\n",
|
|
350
|
+
" font-size: 0.6rem;\n",
|
|
351
|
+
" font-weight: lighter;\n",
|
|
352
|
+
" color: var(--sklearn-color-text-muted);\n",
|
|
353
|
+
"}\n",
|
|
354
|
+
"\n",
|
|
355
|
+
"#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
|
|
356
|
+
" /* Arrow on the left of the label */\n",
|
|
357
|
+
" content: \"▸\";\n",
|
|
358
|
+
" float: left;\n",
|
|
359
|
+
" margin-right: 0.25em;\n",
|
|
360
|
+
" color: var(--sklearn-color-icon);\n",
|
|
361
|
+
"}\n",
|
|
362
|
+
"\n",
|
|
363
|
+
"#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
|
|
364
|
+
" color: var(--sklearn-color-text);\n",
|
|
365
|
+
"}\n",
|
|
366
|
+
"\n",
|
|
367
|
+
"/* Toggleable content - dropdown */\n",
|
|
368
|
+
"\n",
|
|
369
|
+
"#sk-container-id-1 div.sk-toggleable__content {\n",
|
|
370
|
+
" max-height: 0;\n",
|
|
371
|
+
" max-width: 0;\n",
|
|
372
|
+
" overflow: hidden;\n",
|
|
373
|
+
" text-align: left;\n",
|
|
374
|
+
" /* unfitted */\n",
|
|
375
|
+
" background-color: var(--sklearn-color-unfitted-level-0);\n",
|
|
376
|
+
"}\n",
|
|
377
|
+
"\n",
|
|
378
|
+
"#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
|
|
379
|
+
" /* fitted */\n",
|
|
380
|
+
" background-color: var(--sklearn-color-fitted-level-0);\n",
|
|
381
|
+
"}\n",
|
|
382
|
+
"\n",
|
|
383
|
+
"#sk-container-id-1 div.sk-toggleable__content pre {\n",
|
|
384
|
+
" margin: 0.2em;\n",
|
|
385
|
+
" border-radius: 0.25em;\n",
|
|
386
|
+
" color: var(--sklearn-color-text);\n",
|
|
387
|
+
" /* unfitted */\n",
|
|
388
|
+
" background-color: var(--sklearn-color-unfitted-level-0);\n",
|
|
389
|
+
"}\n",
|
|
390
|
+
"\n",
|
|
391
|
+
"#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
|
|
392
|
+
" /* unfitted */\n",
|
|
393
|
+
" background-color: var(--sklearn-color-fitted-level-0);\n",
|
|
394
|
+
"}\n",
|
|
395
|
+
"\n",
|
|
396
|
+
"#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
|
|
397
|
+
" /* Expand drop-down */\n",
|
|
398
|
+
" max-height: 200px;\n",
|
|
399
|
+
" max-width: 100%;\n",
|
|
400
|
+
" overflow: auto;\n",
|
|
401
|
+
"}\n",
|
|
402
|
+
"\n",
|
|
403
|
+
"#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
|
|
404
|
+
" content: \"▾\";\n",
|
|
405
|
+
"}\n",
|
|
406
|
+
"\n",
|
|
407
|
+
"/* Pipeline/ColumnTransformer-specific style */\n",
|
|
408
|
+
"\n",
|
|
409
|
+
"#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
|
|
410
|
+
" color: var(--sklearn-color-text);\n",
|
|
411
|
+
" background-color: var(--sklearn-color-unfitted-level-2);\n",
|
|
412
|
+
"}\n",
|
|
413
|
+
"\n",
|
|
414
|
+
"#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
|
|
415
|
+
" background-color: var(--sklearn-color-fitted-level-2);\n",
|
|
416
|
+
"}\n",
|
|
417
|
+
"\n",
|
|
418
|
+
"/* Estimator-specific style */\n",
|
|
419
|
+
"\n",
|
|
420
|
+
"/* Colorize estimator box */\n",
|
|
421
|
+
"#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
|
|
422
|
+
" /* unfitted */\n",
|
|
423
|
+
" background-color: var(--sklearn-color-unfitted-level-2);\n",
|
|
424
|
+
"}\n",
|
|
425
|
+
"\n",
|
|
426
|
+
"#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
|
|
427
|
+
" /* fitted */\n",
|
|
428
|
+
" background-color: var(--sklearn-color-fitted-level-2);\n",
|
|
429
|
+
"}\n",
|
|
430
|
+
"\n",
|
|
431
|
+
"#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
|
|
432
|
+
"#sk-container-id-1 div.sk-label label {\n",
|
|
433
|
+
" /* The background is the default theme color */\n",
|
|
434
|
+
" color: var(--sklearn-color-text-on-default-background);\n",
|
|
435
|
+
"}\n",
|
|
436
|
+
"\n",
|
|
437
|
+
"/* On hover, darken the color of the background */\n",
|
|
438
|
+
"#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
|
|
439
|
+
" color: var(--sklearn-color-text);\n",
|
|
440
|
+
" background-color: var(--sklearn-color-unfitted-level-2);\n",
|
|
441
|
+
"}\n",
|
|
442
|
+
"\n",
|
|
443
|
+
"/* Label box, darken color on hover, fitted */\n",
|
|
444
|
+
"#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
|
|
445
|
+
" color: var(--sklearn-color-text);\n",
|
|
446
|
+
" background-color: var(--sklearn-color-fitted-level-2);\n",
|
|
447
|
+
"}\n",
|
|
448
|
+
"\n",
|
|
449
|
+
"/* Estimator label */\n",
|
|
450
|
+
"\n",
|
|
451
|
+
"#sk-container-id-1 div.sk-label label {\n",
|
|
452
|
+
" font-family: monospace;\n",
|
|
453
|
+
" font-weight: bold;\n",
|
|
454
|
+
" display: inline-block;\n",
|
|
455
|
+
" line-height: 1.2em;\n",
|
|
456
|
+
"}\n",
|
|
457
|
+
"\n",
|
|
458
|
+
"#sk-container-id-1 div.sk-label-container {\n",
|
|
459
|
+
" text-align: center;\n",
|
|
460
|
+
"}\n",
|
|
461
|
+
"\n",
|
|
462
|
+
"/* Estimator-specific */\n",
|
|
463
|
+
"#sk-container-id-1 div.sk-estimator {\n",
|
|
464
|
+
" font-family: monospace;\n",
|
|
465
|
+
" border: 1px dotted var(--sklearn-color-border-box);\n",
|
|
466
|
+
" border-radius: 0.25em;\n",
|
|
467
|
+
" box-sizing: border-box;\n",
|
|
468
|
+
" margin-bottom: 0.5em;\n",
|
|
469
|
+
" /* unfitted */\n",
|
|
470
|
+
" background-color: var(--sklearn-color-unfitted-level-0);\n",
|
|
471
|
+
"}\n",
|
|
472
|
+
"\n",
|
|
473
|
+
"#sk-container-id-1 div.sk-estimator.fitted {\n",
|
|
474
|
+
" /* fitted */\n",
|
|
475
|
+
" background-color: var(--sklearn-color-fitted-level-0);\n",
|
|
476
|
+
"}\n",
|
|
477
|
+
"\n",
|
|
478
|
+
"/* on hover */\n",
|
|
479
|
+
"#sk-container-id-1 div.sk-estimator:hover {\n",
|
|
480
|
+
" /* unfitted */\n",
|
|
481
|
+
" background-color: var(--sklearn-color-unfitted-level-2);\n",
|
|
482
|
+
"}\n",
|
|
483
|
+
"\n",
|
|
484
|
+
"#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
|
|
485
|
+
" /* fitted */\n",
|
|
486
|
+
" background-color: var(--sklearn-color-fitted-level-2);\n",
|
|
487
|
+
"}\n",
|
|
488
|
+
"\n",
|
|
489
|
+
"/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
|
|
490
|
+
"\n",
|
|
491
|
+
"/* Common style for \"i\" and \"?\" */\n",
|
|
492
|
+
"\n",
|
|
493
|
+
".sk-estimator-doc-link,\n",
|
|
494
|
+
"a:link.sk-estimator-doc-link,\n",
|
|
495
|
+
"a:visited.sk-estimator-doc-link {\n",
|
|
496
|
+
" float: right;\n",
|
|
497
|
+
" font-size: smaller;\n",
|
|
498
|
+
" line-height: 1em;\n",
|
|
499
|
+
" font-family: monospace;\n",
|
|
500
|
+
" background-color: var(--sklearn-color-background);\n",
|
|
501
|
+
" border-radius: 1em;\n",
|
|
502
|
+
" height: 1em;\n",
|
|
503
|
+
" width: 1em;\n",
|
|
504
|
+
" text-decoration: none !important;\n",
|
|
505
|
+
" margin-left: 0.5em;\n",
|
|
506
|
+
" text-align: center;\n",
|
|
507
|
+
" /* unfitted */\n",
|
|
508
|
+
" border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
|
|
509
|
+
" color: var(--sklearn-color-unfitted-level-1);\n",
|
|
510
|
+
"}\n",
|
|
511
|
+
"\n",
|
|
512
|
+
".sk-estimator-doc-link.fitted,\n",
|
|
513
|
+
"a:link.sk-estimator-doc-link.fitted,\n",
|
|
514
|
+
"a:visited.sk-estimator-doc-link.fitted {\n",
|
|
515
|
+
" /* fitted */\n",
|
|
516
|
+
" border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
|
|
517
|
+
" color: var(--sklearn-color-fitted-level-1);\n",
|
|
518
|
+
"}\n",
|
|
519
|
+
"\n",
|
|
520
|
+
"/* On hover */\n",
|
|
521
|
+
"div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
|
|
522
|
+
".sk-estimator-doc-link:hover,\n",
|
|
523
|
+
"div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
|
|
524
|
+
".sk-estimator-doc-link:hover {\n",
|
|
525
|
+
" /* unfitted */\n",
|
|
526
|
+
" background-color: var(--sklearn-color-unfitted-level-3);\n",
|
|
527
|
+
" color: var(--sklearn-color-background);\n",
|
|
528
|
+
" text-decoration: none;\n",
|
|
529
|
+
"}\n",
|
|
530
|
+
"\n",
|
|
531
|
+
"div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
|
|
532
|
+
".sk-estimator-doc-link.fitted:hover,\n",
|
|
533
|
+
"div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
|
|
534
|
+
".sk-estimator-doc-link.fitted:hover {\n",
|
|
535
|
+
" /* fitted */\n",
|
|
536
|
+
" background-color: var(--sklearn-color-fitted-level-3);\n",
|
|
537
|
+
" color: var(--sklearn-color-background);\n",
|
|
538
|
+
" text-decoration: none;\n",
|
|
539
|
+
"}\n",
|
|
540
|
+
"\n",
|
|
541
|
+
"/* Span, style for the box shown on hovering the info icon */\n",
|
|
542
|
+
".sk-estimator-doc-link span {\n",
|
|
543
|
+
" display: none;\n",
|
|
544
|
+
" z-index: 9999;\n",
|
|
545
|
+
" position: relative;\n",
|
|
546
|
+
" font-weight: normal;\n",
|
|
547
|
+
" right: .2ex;\n",
|
|
548
|
+
" padding: .5ex;\n",
|
|
549
|
+
" margin: .5ex;\n",
|
|
550
|
+
" width: min-content;\n",
|
|
551
|
+
" min-width: 20ex;\n",
|
|
552
|
+
" max-width: 50ex;\n",
|
|
553
|
+
" color: var(--sklearn-color-text);\n",
|
|
554
|
+
" box-shadow: 2pt 2pt 4pt #999;\n",
|
|
555
|
+
" /* unfitted */\n",
|
|
556
|
+
" background: var(--sklearn-color-unfitted-level-0);\n",
|
|
557
|
+
" border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
|
|
558
|
+
"}\n",
|
|
559
|
+
"\n",
|
|
560
|
+
".sk-estimator-doc-link.fitted span {\n",
|
|
561
|
+
" /* fitted */\n",
|
|
562
|
+
" background: var(--sklearn-color-fitted-level-0);\n",
|
|
563
|
+
" border: var(--sklearn-color-fitted-level-3);\n",
|
|
564
|
+
"}\n",
|
|
565
|
+
"\n",
|
|
566
|
+
".sk-estimator-doc-link:hover span {\n",
|
|
567
|
+
" display: block;\n",
|
|
568
|
+
"}\n",
|
|
569
|
+
"\n",
|
|
570
|
+
"/* \"?\"-specific style due to the `<a>` HTML tag */\n",
|
|
571
|
+
"\n",
|
|
572
|
+
"#sk-container-id-1 a.estimator_doc_link {\n",
|
|
573
|
+
" float: right;\n",
|
|
574
|
+
" font-size: 1rem;\n",
|
|
575
|
+
" line-height: 1em;\n",
|
|
576
|
+
" font-family: monospace;\n",
|
|
577
|
+
" background-color: var(--sklearn-color-background);\n",
|
|
578
|
+
" border-radius: 1rem;\n",
|
|
579
|
+
" height: 1rem;\n",
|
|
580
|
+
" width: 1rem;\n",
|
|
581
|
+
" text-decoration: none;\n",
|
|
582
|
+
" /* unfitted */\n",
|
|
583
|
+
" color: var(--sklearn-color-unfitted-level-1);\n",
|
|
584
|
+
" border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
|
|
585
|
+
"}\n",
|
|
586
|
+
"\n",
|
|
587
|
+
"#sk-container-id-1 a.estimator_doc_link.fitted {\n",
|
|
588
|
+
" /* fitted */\n",
|
|
589
|
+
" border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
|
|
590
|
+
" color: var(--sklearn-color-fitted-level-1);\n",
|
|
591
|
+
"}\n",
|
|
592
|
+
"\n",
|
|
593
|
+
"/* On hover */\n",
|
|
594
|
+
"#sk-container-id-1 a.estimator_doc_link:hover {\n",
|
|
595
|
+
" /* unfitted */\n",
|
|
596
|
+
" background-color: var(--sklearn-color-unfitted-level-3);\n",
|
|
597
|
+
" color: var(--sklearn-color-background);\n",
|
|
598
|
+
" text-decoration: none;\n",
|
|
599
|
+
"}\n",
|
|
600
|
+
"\n",
|
|
601
|
+
"#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
|
|
602
|
+
" /* fitted */\n",
|
|
603
|
+
" background-color: var(--sklearn-color-fitted-level-3);\n",
|
|
604
|
+
"}\n",
|
|
605
|
+
"</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestRegressor(random_state=42)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>RandomForestRegressor</div></div><div><a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.6/modules/generated/sklearn.ensemble.RandomForestRegressor.html\">?<span>Documentation for RandomForestRegressor</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\"><pre>RandomForestRegressor(random_state=42)</pre></div> </div></div></div></div>"
|
|
606
|
+
],
|
|
607
|
+
"text/plain": [
|
|
608
|
+
"RandomForestRegressor(random_state=42)"
|
|
609
|
+
]
|
|
610
|
+
},
|
|
611
|
+
"execution_count": 4,
|
|
612
|
+
"metadata": {},
|
|
613
|
+
"output_type": "execute_result"
|
|
614
|
+
}
|
|
615
|
+
],
|
|
616
|
+
"source": [
|
|
617
|
+
"X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2,random_state=42)\n",
|
|
618
|
+
"\n",
|
|
619
|
+
"model=RandomForestRegressor(n_estimators=100,random_state=42)\n",
|
|
620
|
+
"model.fit(X_train,y_train)"
|
|
621
|
+
]
|
|
622
|
+
},
|
|
623
|
+
{
|
|
624
|
+
"cell_type": "code",
|
|
625
|
+
"execution_count": 5,
|
|
626
|
+
"metadata": {
|
|
627
|
+
"colab": {
|
|
628
|
+
"base_uri": "https://localhost:8080/",
|
|
629
|
+
"height": 449
|
|
630
|
+
},
|
|
631
|
+
"id": "a4_Knmz76uyv",
|
|
632
|
+
"outputId": "801f0a25-c327-4f1f-8825-afdd408e1be9"
|
|
633
|
+
},
|
|
634
|
+
"outputs": [
|
|
635
|
+
{
|
|
636
|
+
"data": {
|
|
637
|
+
"image/png": "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",
|
|
638
|
+
"text/plain": [
|
|
639
|
+
"<Figure size 640x480 with 2 Axes>"
|
|
640
|
+
]
|
|
641
|
+
},
|
|
642
|
+
"metadata": {},
|
|
643
|
+
"output_type": "display_data"
|
|
644
|
+
}
|
|
645
|
+
],
|
|
646
|
+
"source": [
|
|
647
|
+
"PartialDependenceDisplay.from_estimator(model,X_train,features=['MedInc'],feature_names=df.columns)\n",
|
|
648
|
+
"plt.show()"
|
|
649
|
+
]
|
|
650
|
+
},
|
|
651
|
+
{
|
|
652
|
+
"cell_type": "code",
|
|
653
|
+
"execution_count": 6,
|
|
654
|
+
"metadata": {
|
|
655
|
+
"colab": {
|
|
656
|
+
"base_uri": "https://localhost:8080/",
|
|
657
|
+
"height": 449
|
|
658
|
+
},
|
|
659
|
+
"id": "OHZdRGxM6w3F",
|
|
660
|
+
"outputId": "9e8afefc-b1f7-4fe4-82ee-09c62f8eb8f0",
|
|
661
|
+
"scrolled": true
|
|
662
|
+
},
|
|
663
|
+
"outputs": [
|
|
664
|
+
{
|
|
665
|
+
"data": {
|
|
666
|
+
"image/png": "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",
|
|
667
|
+
"text/plain": [
|
|
668
|
+
"<Figure size 640x480 with 2 Axes>"
|
|
669
|
+
]
|
|
670
|
+
},
|
|
671
|
+
"metadata": {},
|
|
672
|
+
"output_type": "display_data"
|
|
673
|
+
}
|
|
674
|
+
],
|
|
675
|
+
"source": [
|
|
676
|
+
"PartialDependenceDisplay.from_estimator(model,X_train,[('MedInc','HouseAge')],feature_names=df.columns)\n",
|
|
677
|
+
"plt.show()"
|
|
678
|
+
]
|
|
679
|
+
},
|
|
680
|
+
{
|
|
681
|
+
"cell_type": "markdown",
|
|
682
|
+
"metadata": {
|
|
683
|
+
"id": "GmCsO0lP6-td"
|
|
684
|
+
},
|
|
685
|
+
"source": [
|
|
686
|
+
"**LIME FOR IMAGE**"
|
|
687
|
+
]
|
|
688
|
+
},
|
|
689
|
+
{
|
|
690
|
+
"cell_type": "code",
|
|
691
|
+
"execution_count": 7,
|
|
692
|
+
"metadata": {
|
|
693
|
+
"id": "kKkCLaMW7ANg"
|
|
694
|
+
},
|
|
695
|
+
"outputs": [],
|
|
696
|
+
"source": [
|
|
697
|
+
"from tensorflow.keras.applications.xception import Xception,decode_predictions\n",
|
|
698
|
+
"from tensorflow.keras.datasets import mnist\n",
|
|
699
|
+
"from tensorflow.keras.models import Sequential\n",
|
|
700
|
+
"from tensorflow.keras.layers import Conv2D,MaxPooling2D,Flatten,Dense\n",
|
|
701
|
+
"from tensorflow.keras.utils import to_categorical\n",
|
|
702
|
+
"from lime import lime_image\n",
|
|
703
|
+
"import seaborn as sns\n",
|
|
704
|
+
"from skimage.color import label2rgb\n",
|
|
705
|
+
"import warnings\n",
|
|
706
|
+
"warnings.filterwarnings('ignore')"
|
|
707
|
+
]
|
|
708
|
+
},
|
|
709
|
+
{
|
|
710
|
+
"cell_type": "code",
|
|
711
|
+
"execution_count": 8,
|
|
712
|
+
"metadata": {
|
|
713
|
+
"id": "GgZ51IgYBnP2"
|
|
714
|
+
},
|
|
715
|
+
"outputs": [],
|
|
716
|
+
"source": [
|
|
717
|
+
"(x_train,y_train),(x_test,y_test)=mnist.load_data()\n",
|
|
718
|
+
"\n",
|
|
719
|
+
"x_train=x_train.astype('float32')/255.0\n",
|
|
720
|
+
"x_test=x_test.astype('float32')/255.0\n",
|
|
721
|
+
"\n",
|
|
722
|
+
"y_train_cat=to_categorical(y_train,10)\n",
|
|
723
|
+
"y_test_cat=to_categorical(y_test,10)"
|
|
724
|
+
]
|
|
725
|
+
},
|
|
726
|
+
{
|
|
727
|
+
"cell_type": "code",
|
|
728
|
+
"execution_count": 9,
|
|
729
|
+
"metadata": {
|
|
730
|
+
"colab": {
|
|
731
|
+
"base_uri": "https://localhost:8080/"
|
|
732
|
+
},
|
|
733
|
+
"id": "rABd-7nYENlT",
|
|
734
|
+
"outputId": "9441cc1d-b3a0-4f1b-eaec-fd73b26171e3"
|
|
735
|
+
},
|
|
736
|
+
"outputs": [
|
|
737
|
+
{
|
|
738
|
+
"name": "stdout",
|
|
739
|
+
"output_type": "stream",
|
|
740
|
+
"text": [
|
|
741
|
+
"Epoch 1/2\n",
|
|
742
|
+
"\u001b[1m844/844\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m11s\u001b[0m 11ms/step - accuracy: 0.8629 - loss: 0.4932 - val_accuracy: 0.9767 - val_loss: 0.0903\n",
|
|
743
|
+
"Epoch 2/2\n",
|
|
744
|
+
"\u001b[1m844/844\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 11ms/step - accuracy: 0.9730 - loss: 0.0897 - val_accuracy: 0.9810 - val_loss: 0.0701\n"
|
|
745
|
+
]
|
|
746
|
+
},
|
|
747
|
+
{
|
|
748
|
+
"data": {
|
|
749
|
+
"text/plain": [
|
|
750
|
+
"<keras.src.callbacks.history.History at 0x25535f996d0>"
|
|
751
|
+
]
|
|
752
|
+
},
|
|
753
|
+
"execution_count": 9,
|
|
754
|
+
"metadata": {},
|
|
755
|
+
"output_type": "execute_result"
|
|
756
|
+
}
|
|
757
|
+
],
|
|
758
|
+
"source": [
|
|
759
|
+
"model = Sequential([\n",
|
|
760
|
+
" Conv2D(16, (3, 3), activation='relu', input_shape=(28, 28, 1)),\n",
|
|
761
|
+
" MaxPooling2D((2, 2)),\n",
|
|
762
|
+
" Flatten(),\n",
|
|
763
|
+
" Dense(64, activation='relu'),\n",
|
|
764
|
+
" Dense(10, activation='softmax')\n",
|
|
765
|
+
"])\n",
|
|
766
|
+
"\n",
|
|
767
|
+
"model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])\n",
|
|
768
|
+
"model.fit(x_train, y_train_cat, epochs=2, batch_size=64, validation_split=0.1)\n"
|
|
769
|
+
]
|
|
770
|
+
},
|
|
771
|
+
{
|
|
772
|
+
"cell_type": "code",
|
|
773
|
+
"execution_count": 10,
|
|
774
|
+
"metadata": {
|
|
775
|
+
"colab": {
|
|
776
|
+
"base_uri": "https://localhost:8080/",
|
|
777
|
+
"height": 1000,
|
|
778
|
+
"referenced_widgets": [
|
|
779
|
+
"af45ee093e934a629a993fba7fe2c10f",
|
|
780
|
+
"a332c8bbfb0b4fb18133490edd5000cb",
|
|
781
|
+
"f626defc1d4544b3a8a67c2c792d8c94",
|
|
782
|
+
"465d9a8a9edd4fccb5f7f88d32b7af3f",
|
|
783
|
+
"08e685b6dec343808ab7a34a444f049e",
|
|
784
|
+
"da56cd3d10b741d5a0b383934153357b",
|
|
785
|
+
"4af04f4f3e24470f93f593f71717ccc1",
|
|
786
|
+
"69f13969e1e34139aef8c39f40524d64",
|
|
787
|
+
"9e7e9389e5ff4e2cad706bda44010e1a",
|
|
788
|
+
"57c6b335e2e942f2b4796548d40aefea",
|
|
789
|
+
"79fceb113bc045dd81cbd0861750aa80"
|
|
790
|
+
]
|
|
791
|
+
},
|
|
792
|
+
"id": "WN1BnA68FZ3S",
|
|
793
|
+
"outputId": "5b39ffef-b4d9-41e1-844c-8445d152d736"
|
|
794
|
+
},
|
|
795
|
+
"outputs": [
|
|
796
|
+
{
|
|
797
|
+
"data": {
|
|
798
|
+
"application/vnd.jupyter.widget-view+json": {
|
|
799
|
+
"model_id": "edba83795c68422894d2c0adb1a00689",
|
|
800
|
+
"version_major": 2,
|
|
801
|
+
"version_minor": 0
|
|
802
|
+
},
|
|
803
|
+
"text/plain": [
|
|
804
|
+
" 0%| | 0/1000 [00:00<?, ?it/s]"
|
|
805
|
+
]
|
|
806
|
+
},
|
|
807
|
+
"metadata": {},
|
|
808
|
+
"output_type": "display_data"
|
|
809
|
+
},
|
|
810
|
+
{
|
|
811
|
+
"name": "stdout",
|
|
812
|
+
"output_type": "stream",
|
|
813
|
+
"text": [
|
|
814
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 190ms/step\n",
|
|
815
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 120ms/step\n",
|
|
816
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 67ms/step\n",
|
|
817
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 75ms/step\n",
|
|
818
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 83ms/step\n",
|
|
819
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 84ms/step\n",
|
|
820
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 67ms/step\n",
|
|
821
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 74ms/step\n",
|
|
822
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 63ms/step\n",
|
|
823
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 53ms/step\n",
|
|
824
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step\n",
|
|
825
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step\n",
|
|
826
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step\n",
|
|
827
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step\n",
|
|
828
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step\n",
|
|
829
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 57ms/step\n",
|
|
830
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 53ms/step\n",
|
|
831
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 62ms/step\n",
|
|
832
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step\n",
|
|
833
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step\n",
|
|
834
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 58ms/step\n",
|
|
835
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 51ms/step\n",
|
|
836
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step\n",
|
|
837
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step\n",
|
|
838
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 58ms/step\n",
|
|
839
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step\n",
|
|
840
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 74ms/step\n",
|
|
841
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 63ms/step\n",
|
|
842
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 85ms/step\n",
|
|
843
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 69ms/step\n",
|
|
844
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 62ms/step\n",
|
|
845
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 80ms/step\n",
|
|
846
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 83ms/step\n",
|
|
847
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 76ms/step\n",
|
|
848
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 70ms/step\n",
|
|
849
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 69ms/step\n",
|
|
850
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 73ms/step\n",
|
|
851
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 58ms/step\n",
|
|
852
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 56ms/step\n",
|
|
853
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 57ms/step\n",
|
|
854
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 76ms/step\n",
|
|
855
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 70ms/step\n",
|
|
856
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 82ms/step\n",
|
|
857
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 87ms/step\n",
|
|
858
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 80ms/step\n",
|
|
859
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 67ms/step\n",
|
|
860
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 70ms/step\n",
|
|
861
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 68ms/step\n",
|
|
862
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 68ms/step\n",
|
|
863
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 56ms/step\n",
|
|
864
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 53ms/step\n",
|
|
865
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 56ms/step\n",
|
|
866
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step\n",
|
|
867
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 52ms/step\n",
|
|
868
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 51ms/step\n",
|
|
869
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step\n",
|
|
870
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step\n",
|
|
871
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 68ms/step\n",
|
|
872
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step\n",
|
|
873
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step\n",
|
|
874
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step\n",
|
|
875
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step\n",
|
|
876
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 65ms/step\n",
|
|
877
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 53ms/step\n",
|
|
878
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step\n",
|
|
879
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 53ms/step\n",
|
|
880
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 71ms/step\n",
|
|
881
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 84ms/step\n",
|
|
882
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 70ms/step\n",
|
|
883
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 69ms/step\n",
|
|
884
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step\n",
|
|
885
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step\n",
|
|
886
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 52ms/step\n",
|
|
887
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 63ms/step\n",
|
|
888
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 69ms/step\n",
|
|
889
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step\n",
|
|
890
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step\n",
|
|
891
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 62ms/step\n",
|
|
892
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 53ms/step\n",
|
|
893
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 58ms/step\n",
|
|
894
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step\n",
|
|
895
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 52ms/step\n",
|
|
896
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 66ms/step\n",
|
|
897
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step\n",
|
|
898
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 57ms/step\n",
|
|
899
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 51ms/step\n",
|
|
900
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 58ms/step\n",
|
|
901
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 52ms/step\n",
|
|
902
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 52ms/step\n",
|
|
903
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step\n",
|
|
904
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 57ms/step\n",
|
|
905
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 57ms/step\n",
|
|
906
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step\n",
|
|
907
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 70ms/step\n",
|
|
908
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step\n",
|
|
909
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step\n",
|
|
910
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 56ms/step\n",
|
|
911
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 53ms/step\n",
|
|
912
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 55ms/step\n",
|
|
913
|
+
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 57ms/step\n"
|
|
914
|
+
]
|
|
915
|
+
},
|
|
916
|
+
{
|
|
917
|
+
"data": {
|
|
918
|
+
"image/png": "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",
|
|
919
|
+
"text/plain": [
|
|
920
|
+
"<Figure size 640x480 with 1 Axes>"
|
|
921
|
+
]
|
|
922
|
+
},
|
|
923
|
+
"metadata": {},
|
|
924
|
+
"output_type": "display_data"
|
|
925
|
+
}
|
|
926
|
+
],
|
|
927
|
+
"source": [
|
|
928
|
+
"from lime import lime_image\n",
|
|
929
|
+
"from skimage.color import label2rgb\n",
|
|
930
|
+
"import cv2\n",
|
|
931
|
+
"import numpy as np\n",
|
|
932
|
+
"import matplotlib.pyplot as plt\n",
|
|
933
|
+
"explainer = lime_image.LimeImageExplainer()\n",
|
|
934
|
+
"idx = 25\n",
|
|
935
|
+
"test_image = x_test[idx]\n",
|
|
936
|
+
"\n",
|
|
937
|
+
"# Convert LIME's RGB input back to grayscale\n",
|
|
938
|
+
"predict_fn = lambda x: model.predict(\n",
|
|
939
|
+
" np.array([cv2.cvtColor(img, cv2.COLOR_RGB2GRAY) for img in x])[..., np.newaxis]\n",
|
|
940
|
+
")\n",
|
|
941
|
+
"\n",
|
|
942
|
+
"explanation = explainer.explain_instance(\n",
|
|
943
|
+
" image=test_image.squeeze(), # shape: (28, 28)\n",
|
|
944
|
+
" classifier_fn=predict_fn,\n",
|
|
945
|
+
" top_labels=1,\n",
|
|
946
|
+
" hide_color=0,\n",
|
|
947
|
+
" num_samples=1000\n",
|
|
948
|
+
")\n",
|
|
949
|
+
"\n",
|
|
950
|
+
"temp, mask = explanation.get_image_and_mask(\n",
|
|
951
|
+
" label=explanation.top_labels[0],\n",
|
|
952
|
+
" positive_only=True,\n",
|
|
953
|
+
" hide_rest=False\n",
|
|
954
|
+
")\n",
|
|
955
|
+
"\n",
|
|
956
|
+
"plt.imshow(label2rgb(mask, temp, bg_label=0))\n",
|
|
957
|
+
"plt.title(f\"LIME for label: {y_test[idx]}\")\n",
|
|
958
|
+
"plt.axis('off')\n",
|
|
959
|
+
"plt.show()\n"
|
|
960
|
+
]
|
|
961
|
+
},
|
|
962
|
+
{
|
|
963
|
+
"cell_type": "code",
|
|
964
|
+
"execution_count": null,
|
|
965
|
+
"metadata": {},
|
|
966
|
+
"outputs": [],
|
|
967
|
+
"source": []
|
|
968
|
+
}
|
|
969
|
+
],
|
|
970
|
+
"metadata": {
|
|
971
|
+
"colab": {
|
|
972
|
+
"provenance": []
|
|
973
|
+
},
|
|
974
|
+
"kernelspec": {
|
|
975
|
+
"display_name": "Python 3 (ipykernel)",
|
|
976
|
+
"language": "python",
|
|
977
|
+
"name": "python3"
|
|
978
|
+
},
|
|
979
|
+
"language_info": {
|
|
980
|
+
"codemirror_mode": {
|
|
981
|
+
"name": "ipython",
|
|
982
|
+
"version": 3
|
|
983
|
+
},
|
|
984
|
+
"file_extension": ".py",
|
|
985
|
+
"mimetype": "text/x-python",
|
|
986
|
+
"name": "python",
|
|
987
|
+
"nbconvert_exporter": "python",
|
|
988
|
+
"pygments_lexer": "ipython3",
|
|
989
|
+
"version": "3.12.4"
|
|
990
|
+
},
|
|
991
|
+
"widgets": {
|
|
992
|
+
"application/vnd.jupyter.widget-state+json": {
|
|
993
|
+
"08e685b6dec343808ab7a34a444f049e": {
|
|
994
|
+
"model_module": "@jupyter-widgets/base",
|
|
995
|
+
"model_module_version": "1.2.0",
|
|
996
|
+
"model_name": "LayoutModel",
|
|
997
|
+
"state": {
|
|
998
|
+
"_model_module": "@jupyter-widgets/base",
|
|
999
|
+
"_model_module_version": "1.2.0",
|
|
1000
|
+
"_model_name": "LayoutModel",
|
|
1001
|
+
"_view_count": null,
|
|
1002
|
+
"_view_module": "@jupyter-widgets/base",
|
|
1003
|
+
"_view_module_version": "1.2.0",
|
|
1004
|
+
"_view_name": "LayoutView",
|
|
1005
|
+
"align_content": null,
|
|
1006
|
+
"align_items": null,
|
|
1007
|
+
"align_self": null,
|
|
1008
|
+
"border": null,
|
|
1009
|
+
"bottom": null,
|
|
1010
|
+
"display": null,
|
|
1011
|
+
"flex": null,
|
|
1012
|
+
"flex_flow": null,
|
|
1013
|
+
"grid_area": null,
|
|
1014
|
+
"grid_auto_columns": null,
|
|
1015
|
+
"grid_auto_flow": null,
|
|
1016
|
+
"grid_auto_rows": null,
|
|
1017
|
+
"grid_column": null,
|
|
1018
|
+
"grid_gap": null,
|
|
1019
|
+
"grid_row": null,
|
|
1020
|
+
"grid_template_areas": null,
|
|
1021
|
+
"grid_template_columns": null,
|
|
1022
|
+
"grid_template_rows": null,
|
|
1023
|
+
"height": null,
|
|
1024
|
+
"justify_content": null,
|
|
1025
|
+
"justify_items": null,
|
|
1026
|
+
"left": null,
|
|
1027
|
+
"margin": null,
|
|
1028
|
+
"max_height": null,
|
|
1029
|
+
"max_width": null,
|
|
1030
|
+
"min_height": null,
|
|
1031
|
+
"min_width": null,
|
|
1032
|
+
"object_fit": null,
|
|
1033
|
+
"object_position": null,
|
|
1034
|
+
"order": null,
|
|
1035
|
+
"overflow": null,
|
|
1036
|
+
"overflow_x": null,
|
|
1037
|
+
"overflow_y": null,
|
|
1038
|
+
"padding": null,
|
|
1039
|
+
"right": null,
|
|
1040
|
+
"top": null,
|
|
1041
|
+
"visibility": null,
|
|
1042
|
+
"width": null
|
|
1043
|
+
}
|
|
1044
|
+
},
|
|
1045
|
+
"465d9a8a9edd4fccb5f7f88d32b7af3f": {
|
|
1046
|
+
"model_module": "@jupyter-widgets/controls",
|
|
1047
|
+
"model_module_version": "1.5.0",
|
|
1048
|
+
"model_name": "HTMLModel",
|
|
1049
|
+
"state": {
|
|
1050
|
+
"_dom_classes": [],
|
|
1051
|
+
"_model_module": "@jupyter-widgets/controls",
|
|
1052
|
+
"_model_module_version": "1.5.0",
|
|
1053
|
+
"_model_name": "HTMLModel",
|
|
1054
|
+
"_view_count": null,
|
|
1055
|
+
"_view_module": "@jupyter-widgets/controls",
|
|
1056
|
+
"_view_module_version": "1.5.0",
|
|
1057
|
+
"_view_name": "HTMLView",
|
|
1058
|
+
"description": "",
|
|
1059
|
+
"description_tooltip": null,
|
|
1060
|
+
"layout": "IPY_MODEL_57c6b335e2e942f2b4796548d40aefea",
|
|
1061
|
+
"placeholder": "",
|
|
1062
|
+
"style": "IPY_MODEL_79fceb113bc045dd81cbd0861750aa80",
|
|
1063
|
+
"value": " 1000/1000 [00:16<00:00, 64.22it/s]"
|
|
1064
|
+
}
|
|
1065
|
+
},
|
|
1066
|
+
"4af04f4f3e24470f93f593f71717ccc1": {
|
|
1067
|
+
"model_module": "@jupyter-widgets/controls",
|
|
1068
|
+
"model_module_version": "1.5.0",
|
|
1069
|
+
"model_name": "DescriptionStyleModel",
|
|
1070
|
+
"state": {
|
|
1071
|
+
"_model_module": "@jupyter-widgets/controls",
|
|
1072
|
+
"_model_module_version": "1.5.0",
|
|
1073
|
+
"_model_name": "DescriptionStyleModel",
|
|
1074
|
+
"_view_count": null,
|
|
1075
|
+
"_view_module": "@jupyter-widgets/base",
|
|
1076
|
+
"_view_module_version": "1.2.0",
|
|
1077
|
+
"_view_name": "StyleView",
|
|
1078
|
+
"description_width": ""
|
|
1079
|
+
}
|
|
1080
|
+
},
|
|
1081
|
+
"57c6b335e2e942f2b4796548d40aefea": {
|
|
1082
|
+
"model_module": "@jupyter-widgets/base",
|
|
1083
|
+
"model_module_version": "1.2.0",
|
|
1084
|
+
"model_name": "LayoutModel",
|
|
1085
|
+
"state": {
|
|
1086
|
+
"_model_module": "@jupyter-widgets/base",
|
|
1087
|
+
"_model_module_version": "1.2.0",
|
|
1088
|
+
"_model_name": "LayoutModel",
|
|
1089
|
+
"_view_count": null,
|
|
1090
|
+
"_view_module": "@jupyter-widgets/base",
|
|
1091
|
+
"_view_module_version": "1.2.0",
|
|
1092
|
+
"_view_name": "LayoutView",
|
|
1093
|
+
"align_content": null,
|
|
1094
|
+
"align_items": null,
|
|
1095
|
+
"align_self": null,
|
|
1096
|
+
"border": null,
|
|
1097
|
+
"bottom": null,
|
|
1098
|
+
"display": null,
|
|
1099
|
+
"flex": null,
|
|
1100
|
+
"flex_flow": null,
|
|
1101
|
+
"grid_area": null,
|
|
1102
|
+
"grid_auto_columns": null,
|
|
1103
|
+
"grid_auto_flow": null,
|
|
1104
|
+
"grid_auto_rows": null,
|
|
1105
|
+
"grid_column": null,
|
|
1106
|
+
"grid_gap": null,
|
|
1107
|
+
"grid_row": null,
|
|
1108
|
+
"grid_template_areas": null,
|
|
1109
|
+
"grid_template_columns": null,
|
|
1110
|
+
"grid_template_rows": null,
|
|
1111
|
+
"height": null,
|
|
1112
|
+
"justify_content": null,
|
|
1113
|
+
"justify_items": null,
|
|
1114
|
+
"left": null,
|
|
1115
|
+
"margin": null,
|
|
1116
|
+
"max_height": null,
|
|
1117
|
+
"max_width": null,
|
|
1118
|
+
"min_height": null,
|
|
1119
|
+
"min_width": null,
|
|
1120
|
+
"object_fit": null,
|
|
1121
|
+
"object_position": null,
|
|
1122
|
+
"order": null,
|
|
1123
|
+
"overflow": null,
|
|
1124
|
+
"overflow_x": null,
|
|
1125
|
+
"overflow_y": null,
|
|
1126
|
+
"padding": null,
|
|
1127
|
+
"right": null,
|
|
1128
|
+
"top": null,
|
|
1129
|
+
"visibility": null,
|
|
1130
|
+
"width": null
|
|
1131
|
+
}
|
|
1132
|
+
},
|
|
1133
|
+
"69f13969e1e34139aef8c39f40524d64": {
|
|
1134
|
+
"model_module": "@jupyter-widgets/base",
|
|
1135
|
+
"model_module_version": "1.2.0",
|
|
1136
|
+
"model_name": "LayoutModel",
|
|
1137
|
+
"state": {
|
|
1138
|
+
"_model_module": "@jupyter-widgets/base",
|
|
1139
|
+
"_model_module_version": "1.2.0",
|
|
1140
|
+
"_model_name": "LayoutModel",
|
|
1141
|
+
"_view_count": null,
|
|
1142
|
+
"_view_module": "@jupyter-widgets/base",
|
|
1143
|
+
"_view_module_version": "1.2.0",
|
|
1144
|
+
"_view_name": "LayoutView",
|
|
1145
|
+
"align_content": null,
|
|
1146
|
+
"align_items": null,
|
|
1147
|
+
"align_self": null,
|
|
1148
|
+
"border": null,
|
|
1149
|
+
"bottom": null,
|
|
1150
|
+
"display": null,
|
|
1151
|
+
"flex": null,
|
|
1152
|
+
"flex_flow": null,
|
|
1153
|
+
"grid_area": null,
|
|
1154
|
+
"grid_auto_columns": null,
|
|
1155
|
+
"grid_auto_flow": null,
|
|
1156
|
+
"grid_auto_rows": null,
|
|
1157
|
+
"grid_column": null,
|
|
1158
|
+
"grid_gap": null,
|
|
1159
|
+
"grid_row": null,
|
|
1160
|
+
"grid_template_areas": null,
|
|
1161
|
+
"grid_template_columns": null,
|
|
1162
|
+
"grid_template_rows": null,
|
|
1163
|
+
"height": null,
|
|
1164
|
+
"justify_content": null,
|
|
1165
|
+
"justify_items": null,
|
|
1166
|
+
"left": null,
|
|
1167
|
+
"margin": null,
|
|
1168
|
+
"max_height": null,
|
|
1169
|
+
"max_width": null,
|
|
1170
|
+
"min_height": null,
|
|
1171
|
+
"min_width": null,
|
|
1172
|
+
"object_fit": null,
|
|
1173
|
+
"object_position": null,
|
|
1174
|
+
"order": null,
|
|
1175
|
+
"overflow": null,
|
|
1176
|
+
"overflow_x": null,
|
|
1177
|
+
"overflow_y": null,
|
|
1178
|
+
"padding": null,
|
|
1179
|
+
"right": null,
|
|
1180
|
+
"top": null,
|
|
1181
|
+
"visibility": null,
|
|
1182
|
+
"width": null
|
|
1183
|
+
}
|
|
1184
|
+
},
|
|
1185
|
+
"79fceb113bc045dd81cbd0861750aa80": {
|
|
1186
|
+
"model_module": "@jupyter-widgets/controls",
|
|
1187
|
+
"model_module_version": "1.5.0",
|
|
1188
|
+
"model_name": "DescriptionStyleModel",
|
|
1189
|
+
"state": {
|
|
1190
|
+
"_model_module": "@jupyter-widgets/controls",
|
|
1191
|
+
"_model_module_version": "1.5.0",
|
|
1192
|
+
"_model_name": "DescriptionStyleModel",
|
|
1193
|
+
"_view_count": null,
|
|
1194
|
+
"_view_module": "@jupyter-widgets/base",
|
|
1195
|
+
"_view_module_version": "1.2.0",
|
|
1196
|
+
"_view_name": "StyleView",
|
|
1197
|
+
"description_width": ""
|
|
1198
|
+
}
|
|
1199
|
+
},
|
|
1200
|
+
"9e7e9389e5ff4e2cad706bda44010e1a": {
|
|
1201
|
+
"model_module": "@jupyter-widgets/controls",
|
|
1202
|
+
"model_module_version": "1.5.0",
|
|
1203
|
+
"model_name": "ProgressStyleModel",
|
|
1204
|
+
"state": {
|
|
1205
|
+
"_model_module": "@jupyter-widgets/controls",
|
|
1206
|
+
"_model_module_version": "1.5.0",
|
|
1207
|
+
"_model_name": "ProgressStyleModel",
|
|
1208
|
+
"_view_count": null,
|
|
1209
|
+
"_view_module": "@jupyter-widgets/base",
|
|
1210
|
+
"_view_module_version": "1.2.0",
|
|
1211
|
+
"_view_name": "StyleView",
|
|
1212
|
+
"bar_color": null,
|
|
1213
|
+
"description_width": ""
|
|
1214
|
+
}
|
|
1215
|
+
},
|
|
1216
|
+
"a332c8bbfb0b4fb18133490edd5000cb": {
|
|
1217
|
+
"model_module": "@jupyter-widgets/controls",
|
|
1218
|
+
"model_module_version": "1.5.0",
|
|
1219
|
+
"model_name": "HTMLModel",
|
|
1220
|
+
"state": {
|
|
1221
|
+
"_dom_classes": [],
|
|
1222
|
+
"_model_module": "@jupyter-widgets/controls",
|
|
1223
|
+
"_model_module_version": "1.5.0",
|
|
1224
|
+
"_model_name": "HTMLModel",
|
|
1225
|
+
"_view_count": null,
|
|
1226
|
+
"_view_module": "@jupyter-widgets/controls",
|
|
1227
|
+
"_view_module_version": "1.5.0",
|
|
1228
|
+
"_view_name": "HTMLView",
|
|
1229
|
+
"description": "",
|
|
1230
|
+
"description_tooltip": null,
|
|
1231
|
+
"layout": "IPY_MODEL_da56cd3d10b741d5a0b383934153357b",
|
|
1232
|
+
"placeholder": "",
|
|
1233
|
+
"style": "IPY_MODEL_4af04f4f3e24470f93f593f71717ccc1",
|
|
1234
|
+
"value": "100%"
|
|
1235
|
+
}
|
|
1236
|
+
},
|
|
1237
|
+
"af45ee093e934a629a993fba7fe2c10f": {
|
|
1238
|
+
"model_module": "@jupyter-widgets/controls",
|
|
1239
|
+
"model_module_version": "1.5.0",
|
|
1240
|
+
"model_name": "HBoxModel",
|
|
1241
|
+
"state": {
|
|
1242
|
+
"_dom_classes": [],
|
|
1243
|
+
"_model_module": "@jupyter-widgets/controls",
|
|
1244
|
+
"_model_module_version": "1.5.0",
|
|
1245
|
+
"_model_name": "HBoxModel",
|
|
1246
|
+
"_view_count": null,
|
|
1247
|
+
"_view_module": "@jupyter-widgets/controls",
|
|
1248
|
+
"_view_module_version": "1.5.0",
|
|
1249
|
+
"_view_name": "HBoxView",
|
|
1250
|
+
"box_style": "",
|
|
1251
|
+
"children": [
|
|
1252
|
+
"IPY_MODEL_a332c8bbfb0b4fb18133490edd5000cb",
|
|
1253
|
+
"IPY_MODEL_f626defc1d4544b3a8a67c2c792d8c94",
|
|
1254
|
+
"IPY_MODEL_465d9a8a9edd4fccb5f7f88d32b7af3f"
|
|
1255
|
+
],
|
|
1256
|
+
"layout": "IPY_MODEL_08e685b6dec343808ab7a34a444f049e"
|
|
1257
|
+
}
|
|
1258
|
+
},
|
|
1259
|
+
"da56cd3d10b741d5a0b383934153357b": {
|
|
1260
|
+
"model_module": "@jupyter-widgets/base",
|
|
1261
|
+
"model_module_version": "1.2.0",
|
|
1262
|
+
"model_name": "LayoutModel",
|
|
1263
|
+
"state": {
|
|
1264
|
+
"_model_module": "@jupyter-widgets/base",
|
|
1265
|
+
"_model_module_version": "1.2.0",
|
|
1266
|
+
"_model_name": "LayoutModel",
|
|
1267
|
+
"_view_count": null,
|
|
1268
|
+
"_view_module": "@jupyter-widgets/base",
|
|
1269
|
+
"_view_module_version": "1.2.0",
|
|
1270
|
+
"_view_name": "LayoutView",
|
|
1271
|
+
"align_content": null,
|
|
1272
|
+
"align_items": null,
|
|
1273
|
+
"align_self": null,
|
|
1274
|
+
"border": null,
|
|
1275
|
+
"bottom": null,
|
|
1276
|
+
"display": null,
|
|
1277
|
+
"flex": null,
|
|
1278
|
+
"flex_flow": null,
|
|
1279
|
+
"grid_area": null,
|
|
1280
|
+
"grid_auto_columns": null,
|
|
1281
|
+
"grid_auto_flow": null,
|
|
1282
|
+
"grid_auto_rows": null,
|
|
1283
|
+
"grid_column": null,
|
|
1284
|
+
"grid_gap": null,
|
|
1285
|
+
"grid_row": null,
|
|
1286
|
+
"grid_template_areas": null,
|
|
1287
|
+
"grid_template_columns": null,
|
|
1288
|
+
"grid_template_rows": null,
|
|
1289
|
+
"height": null,
|
|
1290
|
+
"justify_content": null,
|
|
1291
|
+
"justify_items": null,
|
|
1292
|
+
"left": null,
|
|
1293
|
+
"margin": null,
|
|
1294
|
+
"max_height": null,
|
|
1295
|
+
"max_width": null,
|
|
1296
|
+
"min_height": null,
|
|
1297
|
+
"min_width": null,
|
|
1298
|
+
"object_fit": null,
|
|
1299
|
+
"object_position": null,
|
|
1300
|
+
"order": null,
|
|
1301
|
+
"overflow": null,
|
|
1302
|
+
"overflow_x": null,
|
|
1303
|
+
"overflow_y": null,
|
|
1304
|
+
"padding": null,
|
|
1305
|
+
"right": null,
|
|
1306
|
+
"top": null,
|
|
1307
|
+
"visibility": null,
|
|
1308
|
+
"width": null
|
|
1309
|
+
}
|
|
1310
|
+
},
|
|
1311
|
+
"f626defc1d4544b3a8a67c2c792d8c94": {
|
|
1312
|
+
"model_module": "@jupyter-widgets/controls",
|
|
1313
|
+
"model_module_version": "1.5.0",
|
|
1314
|
+
"model_name": "FloatProgressModel",
|
|
1315
|
+
"state": {
|
|
1316
|
+
"_dom_classes": [],
|
|
1317
|
+
"_model_module": "@jupyter-widgets/controls",
|
|
1318
|
+
"_model_module_version": "1.5.0",
|
|
1319
|
+
"_model_name": "FloatProgressModel",
|
|
1320
|
+
"_view_count": null,
|
|
1321
|
+
"_view_module": "@jupyter-widgets/controls",
|
|
1322
|
+
"_view_module_version": "1.5.0",
|
|
1323
|
+
"_view_name": "ProgressView",
|
|
1324
|
+
"bar_style": "success",
|
|
1325
|
+
"description": "",
|
|
1326
|
+
"description_tooltip": null,
|
|
1327
|
+
"layout": "IPY_MODEL_69f13969e1e34139aef8c39f40524d64",
|
|
1328
|
+
"max": 1000,
|
|
1329
|
+
"min": 0,
|
|
1330
|
+
"orientation": "horizontal",
|
|
1331
|
+
"style": "IPY_MODEL_9e7e9389e5ff4e2cad706bda44010e1a",
|
|
1332
|
+
"value": 1000
|
|
1333
|
+
}
|
|
1334
|
+
}
|
|
1335
|
+
}
|
|
1336
|
+
}
|
|
1337
|
+
},
|
|
1338
|
+
"nbformat": 4,
|
|
1339
|
+
"nbformat_minor": 4
|
|
1340
|
+
}
|