diff --git a/.renku/workflow/1c362c8705fa4762b50bb1c5cf955a8d.cwl b/.renku/workflow/1c362c8705fa4762b50bb1c5cf955a8d.cwl new file mode 100644 index 0000000000000000000000000000000000000000..7fd9f01bd2000218cf16e83ab9cea5f4f2261519 --- /dev/null +++ b/.renku/workflow/1c362c8705fa4762b50bb1c5cf955a8d.cwl @@ -0,0 +1,120 @@ +class: Workflow +cwlVersion: v1.0 +hints: [] +inputs: + input_1: + default: states-metadata.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-daily.json + streamable: false + type: string +outputs: + output_0: + outputSource: step_2/output_0 + streamable: false + type: File + output_3: + 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-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 + 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-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 + - *id002 + successCodes: [] + temporaryFailCodes: [] diff --git a/data/covidtracking/states-daily.json b/data/covidtracking/states-daily.json index 6723798333d1d196fc2e3c122a502d2b4f12aa11..5d0f41c7a1527ed3a6a0e9011d9de68ef1c6ac0c 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 sha256:581b2d97d6ae787294c5c3764d6b4803343504cde2d509b8751e70777de4427b -size 19769722 +oid sha256:731bdd982e2f5f8e7aea6d803b7808533636f12afcd5e2cee4654f8c3751d5ef +size 19846967 diff --git a/data/covidtracking/states-metadata.json b/data/covidtracking/states-metadata.json index 0f95736a243bef0bcd994e289776436e69eca25c..fe119668bfb9a733c009637de0996d3028a61d3e 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:ad5953bf232f30a978fd9915c9e87610ace47f93da17b8fd009fcd1c6480f69c -size 123062 +oid sha256:c7e26340ce97cd48bfd991eb59175aab2eb2846dd5ae9d0571ed22de48ca99fc +size 123914 diff --git a/runs/download-covidtracking-data.runs.ipynb b/runs/download-covidtracking-data.runs.ipynb index 137ea109f754078bd09fdaaa0974de00b7996d90..358c216c602355d7f8030f704d62f25afe79474b 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": 5.032173, - "end_time": "2020-11-17T07:42:42.936102", + "duration": 5.400491, + "end_time": "2020-11-18T07:37:20.579115", "exception": false, - "start_time": "2020-11-17T07:42:37.903929", + "start_time": "2020-11-18T07:37:15.178624", "status": "completed" }, "tags": [] @@ -25,10 +25,10 @@ "execution_count": 2, "metadata": { "papermill": { - "duration": 0.029006, - "end_time": "2020-11-17T07:42:42.981669", + "duration": 0.019555, + "end_time": "2020-11-18T07:37:20.610448", "exception": false, - "start_time": "2020-11-17T07:42:42.952663", + "start_time": "2020-11-18T07:37:20.590893", "status": "completed" }, "tags": [ @@ -46,10 +46,10 @@ "execution_count": 3, "metadata": { "papermill": { - "duration": 0.026, - "end_time": "2020-11-17T07:42:43.021237", + "duration": 0.021776, + "end_time": "2020-11-18T07:37:20.639971", "exception": false, - "start_time": "2020-11-17T07:42:42.995237", + "start_time": "2020-11-18T07:37:20.618195", "status": "completed" }, "tags": [ @@ -59,7 +59,7 @@ "outputs": [], "source": [ "# Parameters\n", - "PAPERMILL_INPUT_PATH = \"/tmp/nu8t6zmk/notebooks/process/download-covidtracking-data.ipynb\"\n", + "PAPERMILL_INPUT_PATH = \"/tmp/bze3xo97/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": 0.007143, - "end_time": "2020-11-17T07:42:43.039079", + "duration": 0.008125, + "end_time": "2020-11-18T07:37:20.659954", "exception": false, - "start_time": "2020-11-17T07:42:43.031936", + "start_time": "2020-11-18T07:37:20.651829", "status": "completed" }, "tags": [] @@ -87,10 +87,10 @@ "execution_count": 4, "metadata": { "papermill": { - "duration": 0.399521, - "end_time": "2020-11-17T07:42:43.444673", + "duration": 0.937612, + "end_time": "2020-11-18T07:37:21.604192", "exception": false, - "start_time": "2020-11-17T07:42:43.045152", + "start_time": "2020-11-18T07:37:20.666580", "status": "completed" }, "tags": [] @@ -107,10 +107,10 @@ "execution_count": 5, "metadata": { "papermill": { - "duration": 0.028097, - "end_time": "2020-11-17T07:42:43.488259", + "duration": 0.023584, + "end_time": "2020-11-18T07:37:21.641340", "exception": false, - "start_time": "2020-11-17T07:42:43.460162", + "start_time": "2020-11-18T07:37:21.617756", "status": "completed" }, "tags": [] @@ -129,10 +129,10 @@ "execution_count": 6, "metadata": { "papermill": { - "duration": 0.10648, - "end_time": "2020-11-17T07:42:43.604236", + "duration": 0.069813, + "end_time": "2020-11-18T07:37:21.720161", "exception": false, - "start_time": "2020-11-17T07:42:43.497756", + "start_time": "2020-11-18T07:37:21.650348", "status": "completed" }, "tags": [] @@ -284,10 +284,10 @@ "cell_type": "markdown", "metadata": { "papermill": { - "duration": 0.007903, - "end_time": "2020-11-17T07:42:43.625221", + "duration": 0.007773, + "end_time": "2020-11-18T07:37:21.741178", "exception": false, - "start_time": "2020-11-17T07:42:43.617318", + "start_time": "2020-11-18T07:37:21.733405", "status": "completed" }, "tags": [] @@ -301,10 +301,10 @@ "execution_count": 7, "metadata": { "papermill": { - "duration": 0.649363, - "end_time": "2020-11-17T07:42:44.280699", + "duration": 0.602548, + "end_time": "2020-11-18T07:37:22.350174", "exception": false, - "start_time": "2020-11-17T07:42:43.631336", + "start_time": "2020-11-18T07:37:21.747626", "status": "completed" }, "tags": [] @@ -321,10 +321,10 @@ "execution_count": 8, "metadata": { "papermill": { - "duration": 0.055423, - "end_time": "2020-11-17T07:42:44.355421", + "duration": 0.039808, + "end_time": "2020-11-18T07:37:22.399695", "exception": false, - "start_time": "2020-11-17T07:42:44.299998", + "start_time": "2020-11-18T07:37:22.359887", "status": "completed" }, "tags": [] @@ -343,10 +343,10 @@ "execution_count": 9, "metadata": { "papermill": { - "duration": 0.811442, - "end_time": "2020-11-17T07:42:45.181932", + "duration": 0.612183, + "end_time": "2020-11-18T07:37:23.026970", "exception": false, - "start_time": "2020-11-17T07:42:44.370490", + "start_time": "2020-11-18T07:37:22.414787", "status": "completed" }, "tags": [] @@ -356,7 +356,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "14503 data points\n" + "14559 data points\n" ] }, { @@ -406,21 +406,21 @@ " <tbody>\n", " <tr>\n", " <th>0</th>\n", - " <td>20201116</td>\n", + " <td>20201117</td>\n", " <td>AK</td>\n", - " <td>23240.0</td>\n", + " <td>23874.0</td>\n", " <td>NaN</td>\n", - " <td>849107.0</td>\n", + " <td>854748.0</td>\n", " <td>NaN</td>\n", " <td>totalTestsViral</td>\n", - " <td>872347.0</td>\n", - " <td>143.0</td>\n", - " <td>559.0</td>\n", + " <td>878622.0</td>\n", + " <td>136.0</td>\n", + " <td>562.0</td>\n", " <td>...</td>\n", - " <td>872347</td>\n", - " <td>0</td>\n", - " <td>9</td>\n", - " <td>f9555880eaacb39588e3dbdc1822f7fca35ebf82</td>\n", + " <td>878622</td>\n", + " <td>2</td>\n", + " <td>3</td>\n", + " <td>add5f6d70eaa23eaf0ccf0efc84f91a1a5339805</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>20201116</td>\n", + " <td>20201117</td>\n", " <td>AL</td>\n", - " <td>219232.0</td>\n", - " <td>34587.0</td>\n", - " <td>1281958.0</td>\n", + " <td>220848.0</td>\n", + " <td>34974.0</td>\n", + " <td>1287672.0</td>\n", " <td>NaN</td>\n", " <td>totalTestsViral</td>\n", - " <td>1466603.0</td>\n", - " <td>1262.0</td>\n", + " <td>1473546.0</td>\n", + " <td>1289.0</td>\n", " <td>22716.0</td>\n", " <td>...</td>\n", - " <td>1501190</td>\n", - " <td>1</td>\n", - " <td>441</td>\n", - " <td>6a3bed8bae24c6fd056a322cdf8bdb75b8e91348</td>\n", + " <td>1508520</td>\n", + " <td>52</td>\n", + " <td>0</td>\n", + " <td>c9289d7885721c710a92a383e92c4423ec4d0b2e</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 20201116 AK 23240.0 NaN 849107.0 NaN \n", - "1 20201116 AL 219232.0 34587.0 1281958.0 NaN \n", + "0 20201117 AK 23874.0 NaN 854748.0 NaN \n", + "1 20201117 AL 220848.0 34974.0 1287672.0 NaN \n", "\n", " totalTestResultsSource totalTestResults hospitalizedCurrently \\\n", - "0 totalTestsViral 872347.0 143.0 \n", - "1 totalTestsViral 1466603.0 1262.0 \n", + "0 totalTestsViral 878622.0 136.0 \n", + "1 totalTestsViral 1473546.0 1289.0 \n", "\n", " hospitalizedCumulative ... posNeg deathIncrease hospitalizedIncrease \\\n", - "0 559.0 ... 872347 0 9 \n", - "1 22716.0 ... 1501190 1 441 \n", + "0 562.0 ... 878622 2 3 \n", + "1 22716.0 ... 1508520 52 0 \n", "\n", " hash commercialScore \\\n", - "0 f9555880eaacb39588e3dbdc1822f7fca35ebf82 0 \n", - "1 6a3bed8bae24c6fd056a322cdf8bdb75b8e91348 0 \n", + "0 add5f6d70eaa23eaf0ccf0efc84f91a1a5339805 0 \n", + "1 c9289d7885721c710a92a383e92c4423ec4d0b2e 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": 9.728724, - "end_time": "2020-11-17T07:42:45.610567", + "duration": 10.16274, + "end_time": "2020-11-18T07:37:23.352959", "environment_variables": {}, "exception": null, - "input_path": "/tmp/nu8t6zmk/notebooks/process/download-covidtracking-data.ipynb", + "input_path": "/tmp/bze3xo97/notebooks/process/download-covidtracking-data.ipynb", "output_path": "runs/download-covidtracking-data.runs.ipynb", "parameters": { - "PAPERMILL_INPUT_PATH": "/tmp/nu8t6zmk/notebooks/process/download-covidtracking-data.ipynb", + "PAPERMILL_INPUT_PATH": "/tmp/bze3xo97/notebooks/process/download-covidtracking-data.ipynb", "PAPERMILL_OUTPUT_PATH": "runs/download-covidtracking-data.runs.ipynb", "out_folder": "data/covidtracking" }, - "start_time": "2020-11-17T07:42:35.881843", + "start_time": "2020-11-18T07:37:13.190219", "version": "1.1.0" } },