From 91ecd5ac3db8a27216d4d47bb333022b1e487de1 Mon Sep 17 00:00:00 2001 From: "CR (covid cron)" <beepbop@example.com> Date: Sun, 6 Dec 2020 07:36:46 +0000 Subject: [PATCH] renku rerun data/covidtracking/states-metadata.json data/covidtracking/states-daily.json --- .../1a6aade63cae4283bb644ed4a14adec0.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/1a6aade63cae4283bb644ed4a14adec0.cwl diff --git a/.renku/workflow/1a6aade63cae4283bb644ed4a14adec0.cwl b/.renku/workflow/1a6aade63cae4283bb644ed4a14adec0.cwl new file mode 100644 index 000000000..d2f1ef920 --- /dev/null +++ b/.renku/workflow/1a6aade63cae4283bb644ed4a14adec0.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: states-daily.json + streamable: false + type: string + input_3: + default: out_folder + streamable: false + type: string + input_4: + default: data/covidtracking + streamable: false + type: string + input_5: + default: + class: File + path: ../../notebooks/process/download-covidtracking-data.ipynb + streamable: false + type: File + input_6: + default: runs/download-covidtracking-data.runs.ipynb + streamable: false + type: string +outputs: + output_1: + outputSource: step_3/output_0 + streamable: false + type: File + output_3: + outputSource: step_3/output_1 + streamable: false + type: Directory +requirements: [] +steps: + step_1: + in: + filename: input_1 + input_directory: step_3/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: + filename: input_2 + input_directory: step_3/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: [] + step_3: + in: + input_1: input_3 + input_2: input_4 + input_3: input_5 + input_4: input_6 + out: + - output_1 + - output_0 + run: a17d560c41a54f5aa307ce5f3c5effe5_papermill.cwl diff --git a/data/covidtracking/states-daily.json b/data/covidtracking/states-daily.json index cedfaaa2c..87afbffbe 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:dc1388d54417d825e2fb7d5ac1438d69fc36f8836e13dbb98038fb24f595d243 -size 21181010 +oid sha256:a3628828503580ed48823aa574369330b240f7b22a454de93d09f818461ce7ed +size 21258293 diff --git a/data/covidtracking/states-metadata.json b/data/covidtracking/states-metadata.json index d6b9e29f2..1e43dae89 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:c776456ecf4648944100da79a2131cf140d61c21b2dea66a2cd6a26538a76e69 -size 145428 +oid sha256:8bcfdaa5409e4f9953474c5f60a032653b52d65518107a94d77b82bb2eb334ff +size 146254 diff --git a/runs/download-covidtracking-data.runs.ipynb b/runs/download-covidtracking-data.runs.ipynb index ce8912d37..2d191c18c 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": 5.263478, - "end_time": "2020-12-05T07:37:55.779511", + "duration": 4.717714, + "end_time": "2020-12-06T07:36:42.848851", "exception": false, - "start_time": "2020-12-05T07:37:50.516033", + "start_time": "2020-12-06T07:36:38.131137", "status": "completed" }, "tags": [] @@ -25,10 +25,10 @@ "execution_count": 2, "metadata": { "papermill": { - "duration": 0.020627, - "end_time": "2020-12-05T07:37:55.813877", + "duration": 0.020975, + "end_time": "2020-12-06T07:36:42.884296", "exception": false, - "start_time": "2020-12-05T07:37:55.793250", + "start_time": "2020-12-06T07:36:42.863321", "status": "completed" }, "tags": [ @@ -46,10 +46,10 @@ "execution_count": 3, "metadata": { "papermill": { - "duration": 0.017599, - "end_time": "2020-12-05T07:37:55.839126", + "duration": 0.018155, + "end_time": "2020-12-06T07:36:42.910185", "exception": false, - "start_time": "2020-12-05T07:37:55.821527", + "start_time": "2020-12-06T07:36:42.892030", "status": "completed" }, "tags": [ @@ -59,7 +59,7 @@ "outputs": [], "source": [ "# Parameters\n", - "PAPERMILL_INPUT_PATH = \"/tmp/79vbklhn/notebooks/process/download-covidtracking-data.ipynb\"\n", + "PAPERMILL_INPUT_PATH = \"/tmp/bgj85y8_/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": 0.006687, - "end_time": "2020-12-05T07:37:55.851844", + "duration": 0.005918, + "end_time": "2020-12-06T07:36:42.922347", "exception": false, - "start_time": "2020-12-05T07:37:55.845157", + "start_time": "2020-12-06T07:36:42.916429", "status": "completed" }, "tags": [] @@ -87,10 +87,10 @@ "execution_count": 4, "metadata": { "papermill": { - "duration": 0.75978, - "end_time": "2020-12-05T07:37:56.616186", + "duration": 0.836113, + "end_time": "2020-12-06T07:36:43.763079", "exception": false, - "start_time": "2020-12-05T07:37:55.856406", + "start_time": "2020-12-06T07:36:42.926966", "status": "completed" }, "tags": [] @@ -107,10 +107,10 @@ "execution_count": 5, "metadata": { "papermill": { - "duration": 0.025756, - "end_time": "2020-12-05T07:37:56.656315", + "duration": 0.022803, + "end_time": "2020-12-06T07:36:43.797693", "exception": false, - "start_time": "2020-12-05T07:37:56.630559", + "start_time": "2020-12-06T07:36:43.774890", "status": "completed" }, "tags": [] @@ -129,10 +129,10 @@ "execution_count": 6, "metadata": { "papermill": { - "duration": 0.071889, - "end_time": "2020-12-05T07:37:56.742038", + "duration": 0.104921, + "end_time": "2020-12-06T07:36:43.911415", "exception": false, - "start_time": "2020-12-05T07:37:56.670149", + "start_time": "2020-12-06T07:36:43.806494", "status": "completed" }, "tags": [] @@ -284,10 +284,10 @@ "cell_type": "markdown", "metadata": { "papermill": { - "duration": 0.008185, - "end_time": "2020-12-05T07:37:56.763734", + "duration": 0.007727, + "end_time": "2020-12-06T07:36:43.931182", "exception": false, - "start_time": "2020-12-05T07:37:56.755549", + "start_time": "2020-12-06T07:36:43.923455", "status": "completed" }, "tags": [] @@ -301,10 +301,10 @@ "execution_count": 7, "metadata": { "papermill": { - "duration": 0.73386, - "end_time": "2020-12-05T07:37:57.504423", + "duration": 0.674744, + "end_time": "2020-12-06T07:36:44.611412", "exception": false, - "start_time": "2020-12-05T07:37:56.770563", + "start_time": "2020-12-06T07:36:43.936668", "status": "completed" }, "tags": [] @@ -321,10 +321,10 @@ "execution_count": 8, "metadata": { "papermill": { - "duration": 0.054547, - "end_time": "2020-12-05T07:37:57.575272", + "duration": 0.043869, + "end_time": "2020-12-06T07:36:44.670424", "exception": false, - "start_time": "2020-12-05T07:37:57.520725", + "start_time": "2020-12-06T07:36:44.626555", "status": "completed" }, "tags": [] @@ -343,10 +343,10 @@ "execution_count": 9, "metadata": { "papermill": { - "duration": 0.567192, - "end_time": "2020-12-05T07:37:58.157210", + "duration": 0.584751, + "end_time": "2020-12-06T07:36:45.268667", "exception": false, - "start_time": "2020-12-05T07:37:57.590018", + "start_time": "2020-12-06T07:36:44.683916", "status": "completed" }, "tags": [] @@ -356,7 +356,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "15521 data points\n" + "15577 data points\n" ] }, { @@ -406,21 +406,21 @@ " <tbody>\n", " <tr>\n", " <th>0</th>\n", - " <td>20201204</td>\n", + " <td>20201205</td>\n", " <td>AK</td>\n", - " <td>34041.0</td>\n", + " <td>34963.0</td>\n", " <td>NaN</td>\n", - " <td>1016328.0</td>\n", + " <td>1032268.0</td>\n", " <td>NaN</td>\n", " <td>totalTestsViral</td>\n", - " <td>1050369.0</td>\n", - " <td>151.0</td>\n", - " <td>794.0</td>\n", + " <td>1067231.0</td>\n", + " <td>166.0</td>\n", + " <td>799.0</td>\n", " <td>...</td>\n", - " <td>1050369</td>\n", - " <td>12</td>\n", - " <td>11</td>\n", - " <td>e26ffb8603f9420d79be27ffffa4aff3ba2b2c2d</td>\n", + " <td>1067231</td>\n", + " <td>1</td>\n", + " <td>5</td>\n", + " <td>d8b27967afb185d8e4f38f5209d713ef23065d88</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>20201204</td>\n", + " <td>20201205</td>\n", " <td>AL</td>\n", - " <td>264199.0</td>\n", - " <td>45130.0</td>\n", - " <td>1407299.0</td>\n", + " <td>267589.0</td>\n", + " <td>45785.0</td>\n", + " <td>1415357.0</td>\n", " <td>NaN</td>\n", " <td>totalTestsPeopleViral</td>\n", - " <td>1626368.0</td>\n", - " <td>1875.0</td>\n", + " <td>1637161.0</td>\n", + " <td>1867.0</td>\n", " <td>26331.0</td>\n", " <td>...</td>\n", - " <td>1671498</td>\n", - " <td>55</td>\n", - " <td>269</td>\n", - " <td>fe8f40ae073982f6fce809ac9ed23bc3170f69e8</td>\n", + " <td>1682946</td>\n", + " <td>46</td>\n", + " <td>0</td>\n", + " <td>7a521812788c45e903b5a08f357bdd78f668340a</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 20201204 AK 34041.0 NaN 1016328.0 NaN \n", - "1 20201204 AL 264199.0 45130.0 1407299.0 NaN \n", + "0 20201205 AK 34963.0 NaN 1032268.0 NaN \n", + "1 20201205 AL 267589.0 45785.0 1415357.0 NaN \n", "\n", " totalTestResultsSource totalTestResults hospitalizedCurrently \\\n", - "0 totalTestsViral 1050369.0 151.0 \n", - "1 totalTestsPeopleViral 1626368.0 1875.0 \n", + "0 totalTestsViral 1067231.0 166.0 \n", + "1 totalTestsPeopleViral 1637161.0 1867.0 \n", "\n", " hospitalizedCumulative ... posNeg deathIncrease hospitalizedIncrease \\\n", - "0 794.0 ... 1050369 12 11 \n", - "1 26331.0 ... 1671498 55 269 \n", + "0 799.0 ... 1067231 1 5 \n", + "1 26331.0 ... 1682946 46 0 \n", "\n", " hash commercialScore \\\n", - "0 e26ffb8603f9420d79be27ffffa4aff3ba2b2c2d 0 \n", - "1 fe8f40ae073982f6fce809ac9ed23bc3170f69e8 0 \n", + "0 d8b27967afb185d8e4f38f5209d713ef23065d88 0 \n", + "1 7a521812788c45e903b5a08f357bdd78f668340a 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": 9.691808, - "end_time": "2020-12-05T07:37:58.480279", + "duration": 9.124953, + "end_time": "2020-12-06T07:36:45.590793", "environment_variables": {}, "exception": null, - "input_path": "/tmp/79vbklhn/notebooks/process/download-covidtracking-data.ipynb", + "input_path": "/tmp/bgj85y8_/notebooks/process/download-covidtracking-data.ipynb", "output_path": "runs/download-covidtracking-data.runs.ipynb", "parameters": { - "PAPERMILL_INPUT_PATH": "/tmp/79vbklhn/notebooks/process/download-covidtracking-data.ipynb", + "PAPERMILL_INPUT_PATH": "/tmp/bgj85y8_/notebooks/process/download-covidtracking-data.ipynb", "PAPERMILL_OUTPUT_PATH": "runs/download-covidtracking-data.runs.ipynb", "out_folder": "data/covidtracking" }, - "start_time": "2020-12-05T07:37:48.788471", + "start_time": "2020-12-06T07:36:36.465840", "version": "1.1.0" } }, -- GitLab