From 5d46b5300156c2ec9aadb1660b69b19dcd20dcc8 Mon Sep 17 00:00:00 2001 From: "CR (covid cron)" <beepbop@example.com> Date: Thu, 10 Dec 2020 07:45:08 +0000 Subject: [PATCH] renku rerun data/covidtracking/states-metadata.json data/covidtracking/states-daily.json --- .../d38156548319433aa76d8a44441236bd.cwl | 120 +++++++++++++++ data/covidtracking/states-daily.json | 4 +- data/covidtracking/states-metadata.json | 4 +- runs/download-covidtracking-data.runs.ipynb | 138 +++++++++--------- 4 files changed, 193 insertions(+), 73 deletions(-) create mode 100644 .renku/workflow/d38156548319433aa76d8a44441236bd.cwl diff --git a/.renku/workflow/d38156548319433aa76d8a44441236bd.cwl b/.renku/workflow/d38156548319433aa76d8a44441236bd.cwl new file mode 100644 index 000000000..aac46e302 --- /dev/null +++ b/.renku/workflow/d38156548319433aa76d8a44441236bd.cwl @@ -0,0 +1,120 @@ +class: Workflow +cwlVersion: v1.0 +hints: [] +inputs: + input_1: + default: out_folder + streamable: false + type: string + input_2: + default: data/covidtracking + streamable: false + type: string + input_3: + default: + class: File + path: ../../notebooks/process/download-covidtracking-data.ipynb + streamable: false + type: File + input_4: + default: runs/download-covidtracking-data.runs.ipynb + streamable: false + type: string + input_5: + default: states-daily.json + streamable: false + type: string + input_6: + default: states-metadata.json + streamable: false + type: string +outputs: + output_0: + outputSource: step_1/output_1 + streamable: false + type: Directory + output_2: + outputSource: step_1/output_0 + streamable: false + type: File +requirements: [] +steps: + step_1: + in: + input_1: input_1 + input_2: input_2 + input_3: input_3 + input_4: input_4 + out: + - output_0 + - output_1 + run: a17d560c41a54f5aa307ce5f3c5effe5_papermill.cwl + step_2: + in: + filename: input_5 + input_directory: step_1/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_3: + in: + filename: input_6 + input_directory: step_1/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 9926028e4..3c2976451 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:da333aaf40c0db774f87c0654d56c45e72788eda6bb0ef0b253ecbb9e034b833 -size 21490192 +oid sha256:db2f6e5f2d8c29067e43dc70ea18465841f0a1851b624b085e4d8a891a81bf20 +size 21571126 diff --git a/data/covidtracking/states-metadata.json b/data/covidtracking/states-metadata.json index 81b7319b1..bfe4fe912 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:d97e049d903c4873e23cb051f9be8f2de29dae51670c0dc3002cb95b57e30dad -size 147943 +oid sha256:d9833f5095ca0a847f00ab5622ab1be1ce68bcf61e3005431bb99627cdcd43ec +size 149725 diff --git a/runs/download-covidtracking-data.runs.ipynb b/runs/download-covidtracking-data.runs.ipynb index 1cda5c38f..08cf9764e 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": 4.107006, - "end_time": "2020-12-09T07:40:23.423926", + "duration": 6.57455, + "end_time": "2020-12-10T07:45:03.853676", "exception": false, - "start_time": "2020-12-09T07:40:19.316920", + "start_time": "2020-12-10T07:44:57.279126", "status": "completed" }, "tags": [] @@ -25,10 +25,10 @@ "execution_count": 2, "metadata": { "papermill": { - "duration": 0.023293, - "end_time": "2020-12-09T07:40:23.461454", + "duration": 0.023212, + "end_time": "2020-12-10T07:45:03.894419", "exception": false, - "start_time": "2020-12-09T07:40:23.438161", + "start_time": "2020-12-10T07:45:03.871207", "status": "completed" }, "tags": [ @@ -46,10 +46,10 @@ "execution_count": 3, "metadata": { "papermill": { - "duration": 0.020651, - "end_time": "2020-12-09T07:40:23.493997", + "duration": 0.026984, + "end_time": "2020-12-10T07:45:03.932218", "exception": false, - "start_time": "2020-12-09T07:40:23.473346", + "start_time": "2020-12-10T07:45:03.905234", "status": "completed" }, "tags": [ @@ -59,7 +59,7 @@ "outputs": [], "source": [ "# Parameters\n", - "PAPERMILL_INPUT_PATH = \"/tmp/benfs3jq/notebooks/process/download-covidtracking-data.ipynb\"\n", + "PAPERMILL_INPUT_PATH = \"/tmp/hjio672c/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": 0.007319, - "end_time": "2020-12-09T07:40:23.508686", + "duration": 0.009132, + "end_time": "2020-12-10T07:45:03.952183", "exception": false, - "start_time": "2020-12-09T07:40:23.501367", + "start_time": "2020-12-10T07:45:03.943051", "status": "completed" }, "tags": [] @@ -87,10 +87,10 @@ "execution_count": 4, "metadata": { "papermill": { - "duration": 0.376143, - "end_time": "2020-12-09T07:40:23.889965", + "duration": 0.838065, + "end_time": "2020-12-10T07:45:04.800589", "exception": false, - "start_time": "2020-12-09T07:40:23.513822", + "start_time": "2020-12-10T07:45:03.962524", "status": "completed" }, "tags": [] @@ -107,10 +107,10 @@ "execution_count": 5, "metadata": { "papermill": { - "duration": 0.023167, - "end_time": "2020-12-09T07:40:23.927224", + "duration": 0.031905, + "end_time": "2020-12-10T07:45:04.847192", "exception": false, - "start_time": "2020-12-09T07:40:23.904057", + "start_time": "2020-12-10T07:45:04.815287", "status": "completed" }, "tags": [] @@ -129,10 +129,10 @@ "execution_count": 6, "metadata": { "papermill": { - "duration": 0.070755, - "end_time": "2020-12-09T07:40:24.006782", + "duration": 0.114974, + "end_time": "2020-12-10T07:45:04.976342", "exception": false, - "start_time": "2020-12-09T07:40:23.936027", + "start_time": "2020-12-10T07:45:04.861368", "status": "completed" }, "tags": [] @@ -284,10 +284,10 @@ "cell_type": "markdown", "metadata": { "papermill": { - "duration": 0.007971, - "end_time": "2020-12-09T07:40:24.030072", + "duration": 0.011016, + "end_time": "2020-12-10T07:45:05.004437", "exception": false, - "start_time": "2020-12-09T07:40:24.022101", + "start_time": "2020-12-10T07:45:04.993421", "status": "completed" }, "tags": [] @@ -301,10 +301,10 @@ "execution_count": 7, "metadata": { "papermill": { - "duration": 35.628268, - "end_time": "2020-12-09T07:40:59.665569", + "duration": 0.641805, + "end_time": "2020-12-10T07:45:05.655807", "exception": false, - "start_time": "2020-12-09T07:40:24.037301", + "start_time": "2020-12-10T07:45:05.014002", "status": "completed" }, "tags": [] @@ -321,10 +321,10 @@ "execution_count": 8, "metadata": { "papermill": { - "duration": 0.050121, - "end_time": "2020-12-09T07:40:59.732700", + "duration": 0.055563, + "end_time": "2020-12-10T07:45:05.724800", "exception": false, - "start_time": "2020-12-09T07:40:59.682579", + "start_time": "2020-12-10T07:45:05.669237", "status": "completed" }, "tags": [] @@ -343,10 +343,10 @@ "execution_count": 9, "metadata": { "papermill": { - "duration": 0.623504, - "end_time": "2020-12-09T07:41:00.368713", + "duration": 0.711583, + "end_time": "2020-12-10T07:45:06.452035", "exception": false, - "start_time": "2020-12-09T07:40:59.745209", + "start_time": "2020-12-10T07:45:05.740452", "status": "completed" }, "tags": [] @@ -356,7 +356,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "15745 data points\n" + "15801 data points\n" ] }, { @@ -406,21 +406,21 @@ " <tbody>\n", " <tr>\n", " <th>0</th>\n", - " <td>20201208</td>\n", + " <td>20201209</td>\n", " <td>AK</td>\n", - " <td>36758.0</td>\n", + " <td>37342.0</td>\n", " <td>NaN</td>\n", - " <td>1052220.0</td>\n", + " <td>1062213.0</td>\n", " <td>NaN</td>\n", " <td>totalTestsViral</td>\n", - " <td>1088978.0</td>\n", - " <td>159.0</td>\n", - " <td>827.0</td>\n", + " <td>1099555.0</td>\n", + " <td>165.0</td>\n", + " <td>847.0</td>\n", " <td>...</td>\n", - " <td>1088978</td>\n", - " <td>0</td>\n", - " <td>22</td>\n", - " <td>332692318da328d0239cf8586792c45a6c837366</td>\n", + " <td>1099555</td>\n", + " <td>4</td>\n", + " <td>20</td>\n", + " <td>1ff1db7b83dd9155a28a2e3687fbbb65d619643e</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>20201208</td>\n", + " <td>20201209</td>\n", " <td>AL</td>\n", - " <td>276665.0</td>\n", - " <td>47658.0</td>\n", - " <td>1435083.0</td>\n", + " <td>280187.0</td>\n", + " <td>48648.0</td>\n", + " <td>1441625.0</td>\n", " <td>NaN</td>\n", " <td>totalTestsPeopleViral</td>\n", - " <td>1664090.0</td>\n", - " <td>2097.0</td>\n", - " <td>27323.0</td>\n", + " <td>1673164.0</td>\n", + " <td>2111.0</td>\n", + " <td>27618.0</td>\n", " <td>...</td>\n", - " <td>1711748</td>\n", - " <td>50</td>\n", - " <td>279</td>\n", - " <td>c863532e0b12a00cdb0a9e311c4d17f23651b03f</td>\n", + " <td>1721812</td>\n", + " <td>43</td>\n", + " <td>295</td>\n", + " <td>e16ff21c63db24182a3474993772040770f37424</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 20201208 AK 36758.0 NaN 1052220.0 NaN \n", - "1 20201208 AL 276665.0 47658.0 1435083.0 NaN \n", + "0 20201209 AK 37342.0 NaN 1062213.0 NaN \n", + "1 20201209 AL 280187.0 48648.0 1441625.0 NaN \n", "\n", " totalTestResultsSource totalTestResults hospitalizedCurrently \\\n", - "0 totalTestsViral 1088978.0 159.0 \n", - "1 totalTestsPeopleViral 1664090.0 2097.0 \n", + "0 totalTestsViral 1099555.0 165.0 \n", + "1 totalTestsPeopleViral 1673164.0 2111.0 \n", "\n", " hospitalizedCumulative ... posNeg deathIncrease hospitalizedIncrease \\\n", - "0 827.0 ... 1088978 0 22 \n", - "1 27323.0 ... 1711748 50 279 \n", + "0 847.0 ... 1099555 4 20 \n", + "1 27618.0 ... 1721812 43 295 \n", "\n", " hash commercialScore \\\n", - "0 332692318da328d0239cf8586792c45a6c837366 0 \n", - "1 c863532e0b12a00cdb0a9e311c4d17f23651b03f 0 \n", + "0 1ff1db7b83dd9155a28a2e3687fbbb65d619643e 0 \n", + "1 e16ff21c63db24182a3474993772040770f37424 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": 42.81985, - "end_time": "2020-12-09T07:41:00.692783", + "duration": 13.022997, + "end_time": "2020-12-10T07:45:06.880109", "environment_variables": {}, "exception": null, - "input_path": "/tmp/benfs3jq/notebooks/process/download-covidtracking-data.ipynb", + "input_path": "/tmp/hjio672c/notebooks/process/download-covidtracking-data.ipynb", "output_path": "runs/download-covidtracking-data.runs.ipynb", "parameters": { - "PAPERMILL_INPUT_PATH": "/tmp/benfs3jq/notebooks/process/download-covidtracking-data.ipynb", + "PAPERMILL_INPUT_PATH": "/tmp/hjio672c/notebooks/process/download-covidtracking-data.ipynb", "PAPERMILL_OUTPUT_PATH": "runs/download-covidtracking-data.runs.ipynb", "out_folder": "data/covidtracking" }, - "start_time": "2020-12-09T07:40:17.872933", + "start_time": "2020-12-10T07:44:53.857112", "version": "1.1.0" } }, -- GitLab