-
Notifications
You must be signed in to change notification settings - Fork 0
/
dvc.lock
290 lines (290 loc) · 8.06 KB
/
dvc.lock
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
schema: '2.0'
stages:
get_data:
cmd: python src/stages/data_get.py --config=params.yaml
deps:
- path: src/stages/data_get.py
md5: 79b1180fb658e000f131028d054904e3
size: 1297
- path: src/stages/utils/log.py
md5: e1c8d76c94e2be36d2139d82f9cee9ff
size: 629
params:
params.yaml:
base:
random_state: 42
log_level: INFO
data_load:
dataset_zip: health-dataset.zip
dataset_folder: data/raw
dataset_csv: data/raw/diabetes_data.csv
outs:
- path: data/raw/diabetes_data.csv
md5: 9a9161518e3622deaa5655b42a2a197b
size: 5287141
- path: health-dataset.zip
md5: aa113db36a5123a20a1cb416d749b130
size: 1050035
process_data:
cmd: python src/process_data.py
deps:
- path: health_data/diabetes_data.csv
md5: 9a9161518e3622deaa5655b42a2a197b
size: 5287141
- path: src/process_data.py
md5: d345803603db975791616971274ae166
size: 449
outs:
- path: Processed_data.csv
md5: bec80b6142f1c2df04c60b9ab3f75c2d
size: 4368119
train:
cmd: python src/stages/train.py --config params.yaml
deps:
- path: data/processed/train.csv
md5: 6a5c7defbd522ec508be4464727ccb5e
size: 3453410
- path: src/stages/train.py
md5: 9bf7aa6ef7f61e8d6aaa3bc008062143
size: 1678
- path: src/stages/utils/log.py
md5: e1c8d76c94e2be36d2139d82f9cee9ff
size: 629
- path: src/stages/utils/train.py
md5: 6121d87a5b2daa8689a38332cadad58a
size: 1773
params:
params.yaml:
base:
random_state: 42
log_level: INFO
data_split:
test_size: 0.3
trainset_path: data/processed/train.csv
testset_path: data/processed/test.csv
featurize:
feature_folder: data/processed
features_path: data/processed/featured_data.csv
drop_features:
- Veggies
target_column: Diabetes
train:
cv: 3
estimator_name: xgb
estimators:
logreg:
param_grid:
C:
- 0.1
max_iter:
- 200
solver:
- lbfgs
multi_class:
- multinomial
knn:
param_grid:
n_neighbors:
- 9
xgb:
param_grid:
min_child_weight:
- 1
gamma:
- 1
- 5
subsample:
- 1.0
colsample_bytree:
- 0.6
- 1.0
max_depth:
- 3
dectree:
param_grid:
criterion:
- gini
- entropy
max_depth:
- 8
randforest:
param_grid:
n_estimators:
- 100
max_depth:
- 11
min_samples_split:
- 15
model_folder: model
model_path: model/model.joblib
scaler_path: model/scaler.joblib
outs:
- path: model/model.joblib
md5: 0c3dcab7aa395dd8391c1aaacf7f2d6d
size: 124873
- path: model/scaler.joblib
md5: 034384424b5bd54ec590a37f4caf3f8f
size: 1606
featurize:
cmd: python src/stages/feature_select.py --config params.yaml
deps:
- path: data/raw/diabetes_data.csv
md5: 9a9161518e3622deaa5655b42a2a197b
size: 5287141
- path: src/stages/feature_select.py
md5: be210d913ccbcf256c79ff7fbf24da4a
size: 970
- path: src/stages/utils/log.py
md5: e1c8d76c94e2be36d2139d82f9cee9ff
size: 629
params:
params.yaml:
data_load:
dataset_zip: health-dataset.zip
dataset_folder: data/raw
dataset_csv: data/raw/diabetes_data.csv
featurize:
feature_folder: data/processed
features_path: data/processed/featured_data.csv
drop_features:
- Veggies
target_column: Diabetes
outs:
- path: data/processed/featured_data.csv
md5: d4027581f861aab6fe57755ab8fbfb95
size: 4933672
data_split:
cmd: python src/stages/data_split.py --config params.yaml
deps:
- path: data/processed/featured_data.csv
md5: d4027581f861aab6fe57755ab8fbfb95
size: 4933672
- path: src/stages/data_split.py
md5: f285ddcbd9e76eec5e21ca378a3d26bd
size: 1192
- path: src/stages/utils/log.py
md5: e1c8d76c94e2be36d2139d82f9cee9ff
size: 629
params:
params.yaml:
base:
random_state: 42
log_level: INFO
data_split:
test_size: 0.3
trainset_path: data/processed/train.csv
testset_path: data/processed/test.csv
featurize:
feature_folder: data/processed
features_path: data/processed/featured_data.csv
drop_features:
- Veggies
target_column: Diabetes
outs:
- path: data/processed/test.csv
md5: 55384cfd635be459af11e2738b3d5fd5
size: 1480417
- path: data/processed/train.csv
md5: 6a5c7defbd522ec508be4464727ccb5e
size: 3453410
evaluate:
cmd: python src/stages/evaluate.py --config params.yaml
deps:
- path: data/processed/test.csv
md5: 55384cfd635be459af11e2738b3d5fd5
size: 1480417
- path: model/model.joblib
md5: 0c3dcab7aa395dd8391c1aaacf7f2d6d
size: 124873
- path: model/scaler.joblib
md5: 034384424b5bd54ec590a37f4caf3f8f
size: 1606
- path: src/stages/evaluate.py
md5: 8fc33f15c59e5b197f5aa57ee8995899
size: 2255
- path: src/stages/utils/evaluate.py
md5: 029deb8ce0375be04deb22736831405d
size: 1439
- path: src/stages/utils/log.py
md5: e1c8d76c94e2be36d2139d82f9cee9ff
size: 629
params:
params.yaml:
data_split:
test_size: 0.3
trainset_path: data/processed/train.csv
testset_path: data/processed/test.csv
evaluate:
report_folder: report
accuracy_report_path: report/report.json
confusion_matrix_path: report/confusion_matrix.png
translated_report_path: report/confusion_matrix_data.csv
target_names:
- no_diabetes
- diabetes
featurize:
feature_folder: data/processed
features_path: data/processed/featured_data.csv
drop_features:
- Veggies
target_column: Diabetes
train:
cv: 3
estimator_name: xgb
estimators:
logreg:
param_grid:
C:
- 0.1
max_iter:
- 200
solver:
- lbfgs
multi_class:
- multinomial
knn:
param_grid:
n_neighbors:
- 9
xgb:
param_grid:
min_child_weight:
- 1
gamma:
- 1
- 5
subsample:
- 1.0
colsample_bytree:
- 0.6
- 1.0
max_depth:
- 3
dectree:
param_grid:
criterion:
- gini
- entropy
max_depth:
- 8
randforest:
param_grid:
n_estimators:
- 100
max_depth:
- 11
min_samples_split:
- 15
model_folder: model
model_path: model/model.joblib
scaler_path: model/scaler.joblib
outs:
- path: report/confusion_matrix.png
md5: 4c9d3030f20a5e0fac89a4642a3dfaaa
size: 24628
- path: report/confusion_matrix_data.csv
md5: 74b56f360c6dd4817227e337b92e38e6
size: 442529
- path: report/report.json
md5: a79b40fd99b0928c89f55349b417ff1e
size: 77