From 42ed628b9ad13eb0f51d31682ef1022442f4a998 Mon Sep 17 00:00:00 2001 From: "CR (covid cron)" <beepbop@example.com> Date: Sun, 22 Nov 2020 07:37:29 +0000 Subject: [PATCH] renku rerun data/covidtracking/states-metadata.json data/covidtracking/states-daily.json --- .../65cb477295174a6281baf559bf997f10.cwl | 120 ++++++++++++++++ data/covidtracking/states-daily.json | 4 +- data/covidtracking/states-metadata.json | 4 +- runs/download-covidtracking-data.runs.ipynb | 136 +++++++++--------- 4 files changed, 192 insertions(+), 72 deletions(-) create mode 100644 .renku/workflow/65cb477295174a6281baf559bf997f10.cwl diff --git a/.renku/workflow/65cb477295174a6281baf559bf997f10.cwl b/.renku/workflow/65cb477295174a6281baf559bf997f10.cwl new file mode 100644 index 000000000..274898149 --- /dev/null +++ b/.renku/workflow/65cb477295174a6281baf559bf997f10.cwl @@ -0,0 +1,120 @@ +class: Workflow +cwlVersion: v1.0 +hints: [] +inputs: + input_1: + default: states-daily.json + streamable: false + type: string + input_2: + default: out_folder + streamable: false + type: string + input_3: + default: data/covidtracking + streamable: false + type: string + input_4: + default: + class: File + path: ../../notebooks/process/download-covidtracking-data.ipynb + streamable: false + type: File + input_5: + default: runs/download-covidtracking-data.runs.ipynb + streamable: false + type: string + input_6: + default: states-metadata.json + streamable: false + type: string +outputs: + output_0: + outputSource: step_2/output_0 + streamable: false + type: File + output_2: + outputSource: step_2/output_1 + streamable: false + type: Directory +requirements: [] +steps: + step_1: + in: + filename: input_1 + input_directory: step_2/output_1 + out: + - output_file + run: + arguments: [] + baseCommand: + - 'true' + class: CommandLineTool + cwlVersion: v1.0 + hints: [] + inputs: + filename: + default: states-daily.json + streamable: false + type: string + input_directory: + streamable: false + type: Directory + outputs: + output_file: + outputBinding: + glob: $(inputs.filename) + streamable: false + type: File + permanentFailCodes: [] + requirements: + - &id001 + class: InlineJavascriptRequirement + - &id002 + class: InitialWorkDirRequirement + listing: $(inputs.input_directory.listing) + successCodes: [] + temporaryFailCodes: [] + step_2: + in: + input_1: input_2 + input_2: input_3 + input_3: input_4 + input_4: input_5 + out: + - output_1 + - output_0 + run: a17d560c41a54f5aa307ce5f3c5effe5_papermill.cwl + step_3: + in: + filename: input_6 + input_directory: step_2/output_1 + out: + - output_file + run: + arguments: [] + baseCommand: + - 'true' + class: CommandLineTool + cwlVersion: v1.0 + hints: [] + inputs: + filename: + default: states-metadata.json + streamable: false + type: string + input_directory: + streamable: false + type: Directory + outputs: + output_file: + outputBinding: + glob: $(inputs.filename) + streamable: false + type: File + permanentFailCodes: [] + requirements: + - *id001 + - *id002 + successCodes: [] + temporaryFailCodes: [] diff --git a/data/covidtracking/states-daily.json b/data/covidtracking/states-daily.json index 32934ba40..26f4a230a 100644 --- a/data/covidtracking/states-daily.json +++ b/data/covidtracking/states-daily.json @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7d3309abd61b9b22d466d78f61eb72f18f1deafb021f99284036397b655148fa -size 20081678 +oid sha256:377b6af4da405530763928fe9f18f9d150508fc3944b69d69cbf7e005da51544 +size 20158771 diff --git a/data/covidtracking/states-metadata.json b/data/covidtracking/states-metadata.json index 9017958be..195efa7d8 100644 --- a/data/covidtracking/states-metadata.json +++ b/data/covidtracking/states-metadata.json @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:5582f4bb85af8899ad6a9a70cee9aa8b00dfc9a0088fdb244bb9637a3f94ec59 -size 127025 +oid sha256:58c2665088124cd2c937a5f1c490c4450f3a8d1f0b85a4d0d9acbc91f1810384 +size 127946 diff --git a/runs/download-covidtracking-data.runs.ipynb b/runs/download-covidtracking-data.runs.ipynb index ef83cb13b..9756296f2 100644 --- a/runs/download-covidtracking-data.runs.ipynb +++ b/runs/download-covidtracking-data.runs.ipynb @@ -5,10 +5,10 @@ "execution_count": 1, "metadata": { "papermill": { - "duration": 6.545257, - "end_time": "2020-11-21T07:41:11.579354", + "duration": 4.749163, + "end_time": "2020-11-22T07:36:53.157405", "exception": false, - "start_time": "2020-11-21T07:41:05.034097", + "start_time": "2020-11-22T07:36:48.408242", "status": "completed" }, "tags": [] @@ -25,10 +25,10 @@ "execution_count": 2, "metadata": { "papermill": { - "duration": 0.023318, - "end_time": "2020-11-21T07:41:11.612396", + "duration": 0.020819, + "end_time": "2020-11-22T07:36:53.191032", "exception": false, - "start_time": "2020-11-21T07:41:11.589078", + "start_time": "2020-11-22T07:36:53.170213", "status": "completed" }, "tags": [ @@ -46,10 +46,10 @@ "execution_count": 3, "metadata": { "papermill": { - "duration": 0.020231, - "end_time": "2020-11-21T07:41:11.649536", + "duration": 0.018921, + "end_time": "2020-11-22T07:36:53.217437", "exception": false, - "start_time": "2020-11-21T07:41:11.629305", + "start_time": "2020-11-22T07:36:53.198516", "status": "completed" }, "tags": [ @@ -59,7 +59,7 @@ "outputs": [], "source": [ "# Parameters\n", - "PAPERMILL_INPUT_PATH = \"/tmp/qu6m417e/notebooks/process/download-covidtracking-data.ipynb\"\n", + "PAPERMILL_INPUT_PATH = \"/tmp/gwoumd9n/notebooks/process/download-covidtracking-data.ipynb\"\n", "PAPERMILL_OUTPUT_PATH = \"runs/download-covidtracking-data.runs.ipynb\"\n", "out_folder = \"data/covidtracking\"\n" ] @@ -68,10 +68,10 @@ "cell_type": "markdown", "metadata": { "papermill": { - "duration": 0.008641, - "end_time": "2020-11-21T07:41:11.668486", + "duration": 0.005065, + "end_time": "2020-11-22T07:36:53.228475", "exception": false, - "start_time": "2020-11-21T07:41:11.659845", + "start_time": "2020-11-22T07:36:53.223410", "status": "completed" }, "tags": [] @@ -87,10 +87,10 @@ "execution_count": 4, "metadata": { "papermill": { - "duration": 0.270076, - "end_time": "2020-11-21T07:41:11.944530", + "duration": 0.988163, + "end_time": "2020-11-22T07:36:54.220939", "exception": false, - "start_time": "2020-11-21T07:41:11.674454", + "start_time": "2020-11-22T07:36:53.232776", "status": "completed" }, "tags": [] @@ -107,10 +107,10 @@ "execution_count": 5, "metadata": { "papermill": { - "duration": 0.017829, - "end_time": "2020-11-21T07:41:11.977090", + "duration": 0.022572, + "end_time": "2020-11-22T07:36:54.255117", "exception": false, - "start_time": "2020-11-21T07:41:11.959261", + "start_time": "2020-11-22T07:36:54.232545", "status": "completed" }, "tags": [] @@ -129,10 +129,10 @@ "execution_count": 6, "metadata": { "papermill": { - "duration": 0.073701, - "end_time": "2020-11-21T07:41:12.056774", + "duration": 0.07183, + "end_time": "2020-11-22T07:36:54.335970", "exception": false, - "start_time": "2020-11-21T07:41:11.983073", + "start_time": "2020-11-22T07:36:54.264140", "status": "completed" }, "tags": [] @@ -284,10 +284,10 @@ "cell_type": "markdown", "metadata": { "papermill": { - "duration": 0.007285, - "end_time": "2020-11-21T07:41:12.073365", + "duration": 0.006726, + "end_time": "2020-11-22T07:36:54.354334", "exception": false, - "start_time": "2020-11-21T07:41:12.066080", + "start_time": "2020-11-22T07:36:54.347608", "status": "completed" }, "tags": [] @@ -301,10 +301,10 @@ "execution_count": 7, "metadata": { "papermill": { - "duration": 0.486251, - "end_time": "2020-11-21T07:41:12.567821", + "duration": 33.373785, + "end_time": "2020-11-22T07:37:27.734288", "exception": false, - "start_time": "2020-11-21T07:41:12.081570", + "start_time": "2020-11-22T07:36:54.360503", "status": "completed" }, "tags": [] @@ -321,10 +321,10 @@ "execution_count": 8, "metadata": { "papermill": { - "duration": 0.079999, - "end_time": "2020-11-21T07:41:12.666722", + "duration": 0.051596, + "end_time": "2020-11-22T07:37:27.802794", "exception": false, - "start_time": "2020-11-21T07:41:12.586723", + "start_time": "2020-11-22T07:37:27.751198", "status": "completed" }, "tags": [] @@ -343,10 +343,10 @@ "execution_count": 9, "metadata": { "papermill": { - "duration": 0.775336, - "end_time": "2020-11-21T07:41:13.460390", + "duration": 0.501441, + "end_time": "2020-11-22T07:37:28.316489", "exception": false, - "start_time": "2020-11-21T07:41:12.685054", + "start_time": "2020-11-22T07:37:27.815048", "status": "completed" }, "tags": [] @@ -356,7 +356,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "14729 data points\n" + "14785 data points\n" ] }, { @@ -406,21 +406,21 @@ " <tbody>\n", " <tr>\n", " <th>0</th>\n", - " <td>20201120</td>\n", + " <td>20201121</td>\n", " <td>AK</td>\n", - " <td>25369.0</td>\n", + " <td>26044.0</td>\n", " <td>NaN</td>\n", - " <td>879343.0</td>\n", + " <td>892701.0</td>\n", " <td>NaN</td>\n", " <td>totalTestsViral</td>\n", - " <td>904712.0</td>\n", - " <td>127.0</td>\n", - " <td>606.0</td>\n", + " <td>918745.0</td>\n", + " <td>129.0</td>\n", + " <td>612.0</td>\n", " <td>...</td>\n", - " <td>904712</td>\n", - " <td>0</td>\n", - " <td>13</td>\n", - " <td>69903ec40b2eb2629d77fa81ecaea343e862a768</td>\n", + " <td>918745</td>\n", + " <td>1</td>\n", + " <td>6</td>\n", + " <td>0d51b28ef5ce194e5dc76dcf4e15162d75123d17</td>\n", " <td>0</td>\n", " <td>0</td>\n", " <td>0</td>\n", @@ -430,21 +430,21 @@ " </tr>\n", " <tr>\n", " <th>1</th>\n", - " <td>20201120</td>\n", + " <td>20201121</td>\n", " <td>AL</td>\n", - " <td>228373.0</td>\n", - " <td>36965.0</td>\n", - " <td>1316804.0</td>\n", + " <td>230708.0</td>\n", + " <td>37613.0</td>\n", + " <td>1325091.0</td>\n", " <td>NaN</td>\n", " <td>totalTestsViral</td>\n", - " <td>1508212.0</td>\n", - " <td>1329.0</td>\n", + " <td>1518186.0</td>\n", + " <td>1300.0</td>\n", " <td>23449.0</td>\n", " <td>...</td>\n", - " <td>1545177</td>\n", - " <td>32</td>\n", - " <td>154</td>\n", - " <td>f80f4da63db3493044b482c48fbd160331904b94</td>\n", + " <td>1555799</td>\n", + " <td>6</td>\n", + " <td>0</td>\n", + " <td>659435bfb739cc4892ee95aef1a62ff35977768a</td>\n", " <td>0</td>\n", " <td>0</td>\n", " <td>0</td>\n", @@ -459,20 +459,20 @@ ], "text/plain": [ " date state positive probableCases negative pending \\\n", - "0 20201120 AK 25369.0 NaN 879343.0 NaN \n", - "1 20201120 AL 228373.0 36965.0 1316804.0 NaN \n", + "0 20201121 AK 26044.0 NaN 892701.0 NaN \n", + "1 20201121 AL 230708.0 37613.0 1325091.0 NaN \n", "\n", " totalTestResultsSource totalTestResults hospitalizedCurrently \\\n", - "0 totalTestsViral 904712.0 127.0 \n", - "1 totalTestsViral 1508212.0 1329.0 \n", + "0 totalTestsViral 918745.0 129.0 \n", + "1 totalTestsViral 1518186.0 1300.0 \n", "\n", " hospitalizedCumulative ... posNeg deathIncrease hospitalizedIncrease \\\n", - "0 606.0 ... 904712 0 13 \n", - "1 23449.0 ... 1545177 32 154 \n", + "0 612.0 ... 918745 1 6 \n", + "1 23449.0 ... 1555799 6 0 \n", "\n", " hash commercialScore \\\n", - "0 69903ec40b2eb2629d77fa81ecaea343e862a768 0 \n", - "1 f80f4da63db3493044b482c48fbd160331904b94 0 \n", + "0 0d51b28ef5ce194e5dc76dcf4e15162d75123d17 0 \n", + "1 659435bfb739cc4892ee95aef1a62ff35977768a 0 \n", "\n", " negativeRegularScore negativeScore positiveScore score grade \n", "0 0 0 0 0 \n", @@ -512,18 +512,18 @@ "version": "3.7.3" }, "papermill": { - "duration": 11.243961, - "end_time": "2020-11-21T07:41:13.886011", + "duration": 41.94801, + "end_time": "2020-11-22T07:37:28.640711", "environment_variables": {}, "exception": null, - "input_path": "/tmp/qu6m417e/notebooks/process/download-covidtracking-data.ipynb", + "input_path": "/tmp/gwoumd9n/notebooks/process/download-covidtracking-data.ipynb", "output_path": "runs/download-covidtracking-data.runs.ipynb", "parameters": { - "PAPERMILL_INPUT_PATH": "/tmp/qu6m417e/notebooks/process/download-covidtracking-data.ipynb", + "PAPERMILL_INPUT_PATH": "/tmp/gwoumd9n/notebooks/process/download-covidtracking-data.ipynb", "PAPERMILL_OUTPUT_PATH": "runs/download-covidtracking-data.runs.ipynb", "out_folder": "data/covidtracking" }, - "start_time": "2020-11-21T07:41:02.642050", + "start_time": "2020-11-22T07:36:46.692701", "version": "1.1.0" } }, -- GitLab