Register
Login
Resources
Docs Blog Datasets Glossary Case Studies Tutorials & Webinars
Product
Data Engine LLMs Platform Enterprise
Pricing Explore
Connect to our Discord channel
Resources  
Docs Blog Datasets Glossary Case Studies Tutorials & Webinars
Explore Pricing
Product  
Data Engine LLMs Platform Enterprise
Connect to Dagshub Discord channel
Register
Login

jnirschl
/
titanic_dvc
mirror of https://github.com/jnirschl/titanic_dvc.git

Watch 1
Issues   Discussions 0

dvc.lock 6.8 KB
Permalink History Raw

You have to be logged in to leave a comment. Sign In
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 
  1. schema: '2.0'
    2. 

  2. stages:
    3. 

  3.   make_dataset:
    4. 

  4.     cmd: python3 src/data/make_dataset.py -c titanic -tr train.csv -te test.csv -o
    5. 

  5.       ./data/raw
    6. 

  6.     deps:
    7. 

  7.     - path: src/data/make_dataset.py
    8. 

  8.       md5: 6003407559d33e14c4122af507648dfd
    9. 

  9.       size: 2280
    10. 

  10.     params:
    11. 

  11.       params.yaml:
    12. 

  12.         dtypes:
    13. 

  13.           Age: float
    14. 

  14.           Embarked: category
    15. 

  15.           Fare: float
    16. 

  16.           Parch: int
    17. 

  17.           Pclass: category
    18. 

  18.           Sex: category
    19. 

  19.           SibSp: int
    20. 

  20.           Survived: category
    21. 

  21.     outs:
    22. 

  22.     - path: data/raw/test.csv
    23. 

  23.       md5: 029c9cd22461f6dbe8d9ab01def965c6
    24. 

  24.       size: 28629
    25. 

  25.     - path: data/raw/train.csv
    26. 

  26.       md5: 61fdd54abdbf6a85b778e937122e1194
    27. 

  27.       size: 61194
    28. 

  28.     - path: reports/figures/data_dictionary.tex
    29. 

  29.       md5: 10c5361db59b330722bd70b83ce0fcee
    30. 

  30.       size: 1521
    31. 

  31.     - path: reports/figures/table_one.tex
    32. 

  32.       md5: 4581508bdb37e12d9b9b5ff03244390d
    33. 

  33.       size: 844
    34. 

  34.   encode_labels:
    35. 

  35.     cmd: python3 src/data/encode_labels.py -tr data/raw/train.csv -te data/raw/test.csv
    36. 

  36.       -o data/interim
    37. 

  37.     deps:
    38. 

  38.     - path: data/raw/test.csv
    39. 

  39.       md5: 029c9cd22461f6dbe8d9ab01def965c6
    40. 

  40.       size: 28629
    41. 

  41.     - path: data/raw/train.csv
    42. 

  42.       md5: 61fdd54abdbf6a85b778e937122e1194
    43. 

  43.       size: 61194
    44. 

  44.     - path: src/data/encode_labels.py
    45. 

  45.       md5: 94202f6ff677094ae0bf8b98575baf50
    46. 

  46.       size: 3623
    47. 

  47.     params:
    48. 

  48.       params.yaml:
    49. 

  49.         dtypes:
    50. 

  50.           Age: float
    51. 

  51.           Embarked: category
    52. 

  52.           Fare: float
    53. 

  53.           Parch: int
    54. 

  54.           Pclass: category
    55. 

  55.           Sex: category
    56. 

  56.           SibSp: int
    57. 

  57.           Survived: category
    58. 

  58.     outs:
    59. 

  59.     - path: data/interim/label_encoding.yaml
    60. 

  60.       md5: 8e736d94ad872a9a10f2321653990609
    61. 

  61.       size: 115
    62. 

  62.     - path: data/interim/test_categorized.csv
    63. 

  63.       md5: f0fcdcd7bb08c23d382a665ac1436034
    64. 

  64.       size: 10788
    65. 

  65.     - path: data/interim/train_categorized.csv
    66. 

  66.       md5: 5d06666c95fed743140b44190fb67c77
    67. 

  67.       size: 23884
    68. 

  68.   impute_nan:
    69. 

  69.     cmd: python3 src/data/replace_nan.py -tr data/interim/train_categorized.csv -te
    70. 

  70.       data/interim/test_categorized.csv -o data/interim
    71. 

  71.     deps:
    72. 

  72.     - path: data/interim/test_categorized.csv
    73. 

  73.       md5: f0fcdcd7bb08c23d382a665ac1436034
    74. 

  74.       size: 10788
    75. 

  75.     - path: data/interim/train_categorized.csv
    76. 

  76.       md5: 5d06666c95fed743140b44190fb67c77
    77. 

  77.       size: 23884
    78. 

  78.     - path: src/data/replace_nan.py
    79. 

  79.       md5: 76582379c528d402d408982409bd9820
    80. 

  80.       size: 2800
    81. 

  81.     params:
    82. 

  82.       params.yaml:
    83. 

  83.         imputation:
    84. 

  84.           Age: 29.6991
    85. 

  85.           Fare: 32.2042
    86. 

  86.           method: mean
    87. 

  87.     outs:
    88. 

  88.     - path: data/interim/test_nan_imputed.csv
    89. 

  89.       md5: cbc38434c407b0761da80a422ba97cff
    90. 

  90.       size: 11136
    91. 

  91.     - path: data/interim/train_nan_imputed.csv
    92. 

  92.       md5: 9edd0421f46d2f0786ea6d82fdcf4e12
    93. 

  93.       size: 24592
    94. 

  94.   build_features:
    95. 

  95.     cmd: python3 src/features/build_features.py -tr data/interim/train_nan_imputed.csv
    96. 

  96.       -te data/interim/test_nan_imputed.csv -o data/interim/
    97. 

  97.     deps:
    98. 

  98.     - path: data/interim/test_nan_imputed.csv
    99. 

  99.       md5: cbc38434c407b0761da80a422ba97cff
    100. 

  100.       size: 11136
    101. 

  101.     - path: data/interim/train_nan_imputed.csv
    102. 

  102.       md5: 9edd0421f46d2f0786ea6d82fdcf4e12
    103. 

  103.       size: 24592
    104. 

  104.     - path: src/features/build_features.py
    105. 

  105.       md5: 2e6e7d169d77cb1e990fbb37c4f147bd
    106. 

  106.       size: 5030
    107. 

  107.     params:
    108. 

  108.       params.yaml:
    109. 

  109.         feature_eng:
    110. 

  110.           featurize: true
    111. 

  111.         random_seed: 12345
    112. 

  112.     outs:
    113. 

  113.     - path: data/interim/test_featurized.csv
    114. 

  114.       md5: 6879b369c8d9f93c8ddeff61baea9ada
    115. 

  115.       size: 59474
    116. 

  116.     - path: data/interim/train_featurized.csv
    117. 

  117.       md5: 980d370c7991c5b991bf8c47d13beb02
    118. 

  118.       size: 127169
    119. 

  119.   normalize_data:
    120. 

  120.     cmd: python3 src/features/normalize.py -tr data/interim/train_featurized.csv -te
    121. 

  121.       data/interim/test_featurized.csv -o data/processed/
    122. 

  122.     deps:
    123. 

  123.     - path: data/interim/test_featurized.csv
    124. 

  124.       md5: 6879b369c8d9f93c8ddeff61baea9ada
    125. 

  125.       size: 59474
    126. 

  126.     - path: data/interim/train_featurized.csv
    127. 

  127.       md5: 980d370c7991c5b991bf8c47d13beb02
    128. 

  128.       size: 127169
    129. 

  129.     - path: src/features/normalize.py
    130. 

  130.       md5: 1e67fe2375c91a702144569d41a9f9c1
    131. 

  131.       size: 1924
    132. 

  132.     params:
    133. 

  133.       params.yaml:
    134. 

  134.         normalize:
    135. 

  135.     outs:
    136. 

  136.     - path: data/processed/test_processed.csv
    137. 

  137.       md5: 0cb34fc53024fa12b32a098a32870612
    138. 

  138.       size: 59004
    139. 

  139.     - path: data/processed/train_processed.csv
    140. 

  140.       md5: 55fc818f9babfe04c7bd9a605e0f6240
    141. 

  141.       size: 126326
    142. 

  142.   split_train_dev:
    143. 

  143.     cmd: python3 src/data/split_train_dev.py -tr data/processed/train_processed.csv
    144. 

  144.       -o data/processed/
    145. 

  145.     deps:
    146. 

  146.     - path: data/processed/train_processed.csv
    147. 

  147.       md5: 55fc818f9babfe04c7bd9a605e0f6240
    148. 

  148.       size: 126326
    149. 

  149.     - path: src/data/split_train_dev.py
    150. 

  150.       md5: 18368dc893cc1b306e39f62f6d460861
    151. 

  151.       size: 2966
    152. 

  152.     params:
    153. 

  153.       params.yaml:
    154. 

  154.         random_seed: 12345
    155. 

  155.         train_test_split:
    156. 

  156.           n_split: 10
    157. 

  157.           shuffle: true
    158. 

  158.           target_class: Survived
    159. 

  159.     outs:
    160. 

  160.     - path: data/processed/split_train_dev.csv
    161. 

  161.       md5: d4d2c3159380a986fc2f04a8bcffda08
    162. 

  162.       size: 56115
    163. 

  163.   train_model:
    164. 

  164.     cmd: python3 src/models/train_model.py -tr data/processed/train_processed.csv
    165. 

  165.       -cv data/processed/split_train_dev.csv
    166. 

  166.     deps:
    167. 

  167.     - path: data/processed/split_train_dev.csv
    168. 

  168.       md5: d4d2c3159380a986fc2f04a8bcffda08
    169. 

  169.       size: 56115
    170. 

  170.     - path: data/processed/train_processed.csv
    171. 

  171.       md5: 55fc818f9babfe04c7bd9a605e0f6240
    172. 

  172.       size: 126326
    173. 

  173.     - path: src/models/train_model.py
    174. 

  174.       md5: 393a733bef3fbe5b26772193d9450585
    175. 

  175.       size: 4424
    176. 

  176.     params:
    177. 

  177.       params.yaml:
    178. 

  178.         classifier: random_forest
    179. 

  179.         model_params:
    180. 

  180.           logistic_regression:
    181. 

  181.           naive_bayes:
    182. 

  182.           neural_network:
    183. 

  183.           random_forest:
    184. 

  184.             criterion: gini
    185. 

  185.             max_depth: 15
    186. 

  186.             max_features: auto
    187. 

  187.             min_samples_leaf: 6
    188. 

  188.             min_samples_split: 9
    189. 

  189.             n_estimators: 460
    190. 

  190.           support_vector_machine:
    191. 

  191.           xgboost:
    192. 

  192.         random_seed: 12345
    193. 

  193.         train_test_split.target_class: Survived
    194. 

  194.     outs:
    195. 

  195.     - path: models/estimator.pkl
    196. 

  196.       md5: ef34445e0498248f60e9ac3e78093ebe
    197. 

  197.       size: 31660314
    198. 

  198.     - path: results/metrics.json
    199. 

  199.       md5: b836f34107676456da5aded50162522f
    200. 

  200.       size: 316
    201. 

  201.   predict_output:
    202. 

  202.     cmd: python3 src/models/predict.py -te data/processed/test_processed.csv -rd results/
    203. 

  203.       -md models/
    204. 

  204.     deps:
    205. 

  205.     - path: data/processed/test_processed.csv
    206. 

  206.       md5: 0cb34fc53024fa12b32a098a32870612
    207. 

  207.       size: 59004
    208. 

  208.     - path: models/estimator.pkl
    209. 

  209.       md5: ef34445e0498248f60e9ac3e78093ebe
    210. 

  210.       size: 31660314
    211. 

  211.     - path: src/models/metrics.py
    212. 

  212.       md5: 69f52aa7384511f15c07d1504b368643
    213. 

  213.       size: 2056
    214. 

  214.     - path: src/models/predict.py
    215. 

  215.       md5: 3ba9b367a92a19518c0d7fa28426f7a1
    216. 

  216.       size: 3268
    217. 

  217.     params:
    218. 

  218.       params.yaml:
    219. 

  219.         predict:
    220. 

  220.           js_estimator: true
    221. 

  221.         train_test_split.target_class: Survived
    222. 

  222.     outs:
    223. 

  223.     - path: results/test_predict_binary.csv
    224. 

  224.       md5: 76577b506c3bc22a50d1aa61f3b940d0
    225. 

  225.       size: 2839
    226. 

  226.     - path: results/test_predict_proba.csv
    227. 

  227.       md5: 00fb6f7226fc5db2885502f3f44d2bb9
    228. 

  228.       size: 10089
    229.
Prev
Next
Tip!

Press p or to see the previous file or, n or to see the next file

Comments

Write Preview
Loading...
Integrate Google Cloud Storage
Use Google Storage
Select bucket
Upload key
Finish

Use Google Cloud Storage!

Browsing data directories saved to Google Cloud Storage is possible with DAGsHub. Let's configure your repository to easily display your data in the context of any commit!

Specify your Google Storage bucket

Service Account Key

Congratulations!

titanic_dvc is now integrated with Google Cloud Storage!

Delete Storage Key

Are you sure you want to delete this access key?

No
Yes
Integrate AWS S3
Use S3 remote
Select bucket
Access key
Finish

Use AWS S3 as storage!

Browsing data directories saved to S3 is possible with DAGsHub. Let's configure your repository to easily display your data in the context of any commit!

Specify your S3 bucket

Access key (If needed)

Congratulations!

titanic_dvc is now integrated with AWS S3!

Delete Storage Key

Are you sure you want to delete this access key?

No
Yes
Integrate S3 compatible storage
Use S3 like remote
Select bucket
Access key
Finish

Use any S3 compatible storage!

Browsing data directories saved to S3 compatible storage is possible with DAGsHub. Let's configure your repository to easily display your data in the context of any commit!

Specify your S3 bucket

Access key (If needed)

Congratulations!

titanic_dvc is now integrated with your S3 compatible storage!

Delete Storage Key

Are you sure you want to delete this access key?

No
Yes
Integrate Azure Cloud Storage
Use Azure Storage
Select bucket
Set key
Finish

Use Azure Cloud Storage!

Browsing data directories saved to Azure Cloud Storage is possible with DAGsHub. Let's configure your repository to easily display your data in the context of any commit!

Specify your Azure Storage bucket

Access key (If needed)

Congratulations!

titanic_dvc is now integrated with Azure Cloud Storage!

Delete Storage Key

Are you sure you want to delete this access key?

No
Yes