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

mraxilus
/
thesis-doctorate
mirror of https://gitlab.com/mraxilus/thesis-doctorate.git

Watch 1
Discussions 0

dvc.yaml 6.6 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 
  1. ---
    2. 

  2. vars:
    3. 

  3.   - datasets:
    4. 

  4.       - air
    5. 

  5.       - synthetic
    6. 

  6.       - water
    7. 

  7. 

  8. stages:
    9. 

  9.   # Process, clean, or generate data to be used for prediction.
    10. 

  10.   clean:
    11. 

  11.     foreach: ${datasets}
    12. 

  12.     do:
    13. 

  13.       cmd: ./data/${item}/script/clean.py
    14. 

  14.       deps:
    15. 

  15.         - data/${item}/raw
    16. 

  16.         - data/${item}/script/clean.py
    17. 

  17.       outs:
    18. 

  18.         - data/${item}/clean/multivariate.parquet
    19. 

  19.         - data/${item}/clean/univariate.parquet
    20. 

  20. 

  21.   # Convert clean data into a format suitable for modelling process.
    22. 

  22.   parameterize:
    23. 

  23.     foreach: ${datasets}
    24. 

  24.     do:
    25. 

  25.       cmd: ./source/thesis/data/parameterize.py
    26. 

  26.         --path_source data/${item}/clean/univariate.parquet
    27. 

  27.         --path_destination data/${item}/clean/univariate_parameterized.parquet
    28. 

  28.       params:
    29. 

  29.         - aggregations
    30. 

  30.       deps:
    31. 

  31.         - data/${item}/clean/univariate.parquet
    32. 

  32.         - source/thesis/data/parameterize.py
    33. 

  33.       outs:
    34. 

  34.         - data/${item}/clean/univariate_parameterized.parquet
    35. 

  35. 

  36.   # Determine ground truth to compare model predictions against.
    37. 

  37.   establish:
    38. 

  38.     foreach: ${datasets}
    39. 

  39.     do:
    40. 

  40.       cmd: ./source/thesis/data/establish.py
    41. 

  41.         --path_source data/${item}/clean/univariate_parameterized.parquet
    42. 

  42.         --path_destination data/${item}/clean/univariate_ground_truth.parquet
    43. 

  43.       params:
    44. 

  44.         - aggregations
    45. 

  45.       deps:
    46. 

  46.         - data/${item}/clean/univariate_parameterized.parquet
    47. 

  47.         - source/thesis/data/establish.py
    48. 

  48.       outs:
    49. 

  49.         - data/${item}/clean/univariate_ground_truth.parquet
    50. 

  50. 

  51.   # Train models and store predictions in appropriate format.
    52. 

  52.   predict_naive:
    53. 

  53.     foreach: ${datasets}
    54. 

  54.     do:
    55. 

  55.       cmd: ./source/thesis/model/predict_naive.py
    56. 

  56.         --path_source data/${item}/clean/univariate_parameterized.parquet
    57. 

  57.         --path_destination data/${item}/clean/univariate_predictions_naive.parquet
    58. 

  58.       params:
    59. 

  59.         - aggregations
    60. 

  60.       deps:
    61. 

  61.         - data/${item}/clean/univariate_parameterized.parquet
    62. 

  62.         - source/thesis/model/predict_naive.py
    63. 

  63.       outs:
    64. 

  64.         - data/${item}/clean/univariate_predictions_naive.parquet
    65. 

  65.   predict_prophet:
    66. 

  66.     foreach: ${datasets}
    67. 

  67.     do:
    68. 

  68.       cmd:
    69. 

  69.         ./source/thesis/model/predict_prophet.py --path_source data/${item}/clean/univariate_parameterized.parquet
    70. 

  70.         --path_destination data/${item}/clean/univariate_predictions_prophet.parquet
    71. 

  71.       params:
    72. 

  72.         - aggregations
    73. 

  73.       deps:
    74. 

  74.         - data/${item}/clean/univariate_parameterized.parquet
    75. 

  75.         - source/thesis/model/predict_prophet.py
    76. 

  76.       outs:
    77. 

  77.         - data/${item}/clean/univariate_predictions_prophet.parquet
    78. 

  78.   # predict_rnn:
    79. 

  79.   #   foreach: ${datasets}
    80. 

  80.   #   do:
    81. 

  81.   #     cmd:
    82. 

  82.   #       ./source/thesis/model/predict_rnn.py --path_source data/${item}/clean/univariate_parameterized.parquet
    83. 

  83.   #       --path_destination data/${item}/clean/univariate_predictions_rnn.parquet
    84. 

  84.   #     params:
    85. 

  85.   #       - aggregations
    86. 

  86.   #     deps:
    87. 

  87.   #       - data/${item}/clean/univariate_parameterized.parquet
    88. 

  88.   #       - source/thesis/model/predict_rnn.py
    89. 

  89.   #     outs:
    90. 

  90.   #       - data/${item}/clean/univariate_predictions_rnn.parquet
    91. 

  91. 

  92.   # Compare model predictions against ground truth; storing errors.
    93. 

  93.   evaluate_naive:
    94. 

  94.     foreach: ${datasets}
    95. 

  95.     do:
    96. 

  96.       cmd: ./source/thesis/data/evaluate.py
    97. 

  97.         --path_ground_truth data/${item}/clean/univariate_ground_truth.parquet
    98. 

  98.         --path_predictions data/${item}/clean/univariate_predictions_naive.parquet
    99. 

  99.         --path_destination data/${item}/clean/univariate_errors_naive.parquet
    100. 

  100.       params:
    101. 

  101.         - aggregations
    102. 

  102.         - metrics
    103. 

  103.       deps:
    104. 

  104.         - data/${item}/clean/univariate_ground_truth.parquet
    105. 

  105.         - data/${item}/clean/univariate_predictions_naive.parquet
    106. 

  106.         - source/thesis/data/evaluate.py
    107. 

  107.       outs:
    108. 

  108.         - data/${item}/clean/univariate_errors_naive.parquet
    109. 

  109.   evaluate_prophet:
    110. 

  110.     foreach: ${datasets}
    111. 

  111.     do:
    112. 

  112.       cmd: ./source/thesis/data/evaluate.py
    113. 

  113.         --path_ground_truth data/${item}/clean/univariate_ground_truth.parquet
    114. 

  114.         --path_predictions data/${item}/clean/univariate_predictions_prophet.parquet
    115. 

  115.         --path_destination data/${item}/clean/univariate_errors_prophet.parquet
    116. 

  116.       params:
    117. 

  117.         - aggregations
    118. 

  118.         - metrics
    119. 

  119.       deps:
    120. 

  120.         - data/${item}/clean/univariate_ground_truth.parquet
    121. 

  121.         - data/${item}/clean/univariate_predictions_prophet.parquet
    122. 

  122.         - source/thesis/data/evaluate.py
    123. 

  123.       outs:
    124. 

  124.         - data/${item}/clean/univariate_errors_prophet.parquet
    125. 

  125.   # evaluate_rnn:
    126. 

  126.   #   foreach: ${datasets}
    127. 

  127.   #   do:
    128. 

  128.   #     cmd:
    129. 

  129.   #       ./source/thesis/data/evaluate.py
    130. 

  130.   #       --path_ground_truth data/${item}/clean/univariate_ground_truth.parquet
    131. 

  131.   #       --path_predictions data/${item}/clean/univariate_predictions_rnn.parquet
    132. 

  132.   #       --path_destination data/${item}/clean/univariate_errors_rnn.parquet
    133. 

  133.   #     params:
    134. 

  134.   #       - aggregations
    135. 

  135.   #       - metrics
    136. 

  136.   #     deps:
    137. 

  137.   #       - data/${item}/clean/univariate_ground_truth.parquet
    138. 

  138.   #       - data/${item}/clean/univariate_predictions_rnn.parquet
    139. 

  139.   #       - source/thesis/data/evaluate.py
    140. 

  140.   #     outs:
    141. 

  141.   #       - data/${item}/clean/univariate_errors_rnn.parquet
    142. 

  142. 

  143.   # Coallesce errors into plotable format for visualisation performance.
    144. 

  144.   tabulate_naive:
    145. 

  145.     foreach: ${datasets}
    146. 

  146.     do:
    147. 

  147.       cmd: ./source/thesis/data/tabulate.py
    148. 

  148.         --path_source data/${item}/clean/univariate_errors_naive.parquet
    149. 

  149.         --path_destination data/${item}/clean/univariate_errors_tabulated_naive.parquet
    150. 

  150.       params:
    151. 

  151.         - aggregations
    152. 

  152.         - metrics
    153. 

  153.         - moments
    154. 

  154.       deps:
    155. 

  155.         - data/${item}/clean/univariate_errors_naive.parquet
    156. 

  156.         - source/thesis/data/tabulate.py
    157. 

  157.       outs:
    158. 

  158.         - data/${item}/clean/univariate_errors_tabulated_naive.parquet
    159. 

  159.   tabulate_prophet:
    160. 

  160.     foreach: ${datasets}
    161. 

  161.     do:
    162. 

  162.       cmd: ./source/thesis/data/tabulate.py
    163. 

  163.         --path_source data/${item}/clean/univariate_errors_prophet.parquet
    164. 

  164.         --path_destination data/${item}/clean/univariate_errors_tabulated_prophet.parquet
    165. 

  165.       params:
    166. 

  166.         - aggregations
    167. 

  167.         - metrics
    168. 

  168.         - moments
    169. 

  169.       deps:
    170. 

  170.         - data/${item}/clean/univariate_errors_prophet.parquet
    171. 

  171.         - source/thesis/data/tabulate.py
    172. 

  172.       outs:
    173. 

  173.         - data/${item}/clean/univariate_errors_tabulated_prophet.parquet
    174. 

  174.   # tabulate_rnn:
    175. 

  175.   #   foreach: ${datasets}
    176. 

  176.   #   do:
    177. 

  177.   #     cmd:
    178. 

  178.   #       ./source/thesis/data/tabulate.py
    179. 

  179.   #       --path_source data/${item}/clean/univariate_errors_rnn.parquet
    180. 

  180.   #       --path_destination data/${item}/clean/univariate_errors_tabulated_rnn.parquet
    181. 

  181.   #     params:
    182. 

  182.   #       - aggregations
    183. 

  183.   #       - metrics
    184. 

  184.   #       - moments
    185. 

  185.   #     deps:
    186. 

  186.   #       - data/${item}/clean/univariate_errors_rnn.parquet
    187. 

  187.   #       - source/thesis/data/tabulate.py
    188. 

  188.   #     outs:
    189. 

  189.   #       - data/${item}/clean/univariate_errors_tabulated_rnn.parquet
    190.
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!

Existing keys:
gs://mraxilus_dvc_public
Feb 03, 2022

Specify your Google Storage bucket

Service Account Key

Congratulations!

thesis-doctorate 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!

thesis-doctorate 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!

thesis-doctorate 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!

thesis-doctorate is now integrated with Azure Cloud Storage!

Delete Storage Key

Are you sure you want to delete this access key?

No
Yes