From 861edaf7e86388e387dbbcd09bb8aeac428d7672 Mon Sep 17 00:00:00 2001 From: "CR (covid cron)" <beepbop@example.com> Date: Thu, 22 Oct 2020 07:38:28 +0000 Subject: [PATCH] renku rerun data/covidtracking/states-metadata.json data/covidtracking/states-daily.json --- .../9f59547fd69f4f239592080ba6152060.cwl | 120 ++++++++++++++++ data/covidtracking/states-daily.json | 4 +- data/covidtracking/states-metadata.json | 4 +- runs/download-covidtracking-data.runs.ipynb | 134 +++++++++--------- 4 files changed, 191 insertions(+), 71 deletions(-) create mode 100644 .renku/workflow/9f59547fd69f4f239592080ba6152060.cwl diff --git a/.renku/workflow/9f59547fd69f4f239592080ba6152060.cwl b/.renku/workflow/9f59547fd69f4f239592080ba6152060.cwl new file mode 100644 index 000000000..95851678e --- /dev/null +++ b/.renku/workflow/9f59547fd69f4f239592080ba6152060.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_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-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 0008f183c..f46f8a866 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 sha256:7624a1e2c0951c2035a1829476c0773330956c8d75eaba8721497f733d16e617 -size 17510251 +oid sha256:df494539d1f415fa97fa4b797e19b344b77a38a26859da7c18709fa6ef5c3610 +size 17664123 diff --git a/data/covidtracking/states-metadata.json b/data/covidtracking/states-metadata.json index 8a80f9556..3c031130f 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:a2a702050c15a7b89f480f9a5985d58a3620ad50b21497614fdaecbfcc82b10d -size 99417 +oid sha256:47af66a052f4bec5112aa6c8fb497518f1e5824d70ba73e3707e0771e792462b +size 101226 diff --git a/runs/download-covidtracking-data.runs.ipynb b/runs/download-covidtracking-data.runs.ipynb index cc45a47e9..ac34098ef 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": 5.449118, - "end_time": "2020-10-20T07:38:33.046345", + "duration": 3.694958, + "end_time": "2020-10-22T07:37:56.023202", "exception": false, - "start_time": "2020-10-20T07:38:27.597227", + "start_time": "2020-10-22T07:37:52.328244", "status": "completed" }, "tags": [] @@ -25,10 +25,10 @@ "execution_count": 2, "metadata": { "papermill": { - "duration": 0.02487, - "end_time": "2020-10-20T07:38:33.088422", + "duration": 0.021365, + "end_time": "2020-10-22T07:37:56.058979", "exception": false, - "start_time": "2020-10-20T07:38:33.063552", + "start_time": "2020-10-22T07:37:56.037614", "status": "completed" }, "tags": [ @@ -46,10 +46,10 @@ "execution_count": 3, "metadata": { "papermill": { - "duration": 0.020621, - "end_time": "2020-10-20T07:38:33.120588", + "duration": 0.020356, + "end_time": "2020-10-22T07:37:56.091110", "exception": false, - "start_time": "2020-10-20T07:38:33.099967", + "start_time": "2020-10-22T07:37:56.070754", "status": "completed" }, "tags": [ @@ -59,7 +59,7 @@ "outputs": [], "source": [ "# Parameters\n", - "PAPERMILL_INPUT_PATH = \"/tmp/m_poq3ob/notebooks/process/download-covidtracking-data.ipynb\"\n", + "PAPERMILL_INPUT_PATH = \"/tmp/apxgwusv/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": 0.006555, - "end_time": "2020-10-20T07:38:33.134837", + "duration": 0.008373, + "end_time": "2020-10-22T07:37:56.107673", "exception": false, - "start_time": "2020-10-20T07:38:33.128282", + "start_time": "2020-10-22T07:37:56.099300", "status": "completed" }, "tags": [] @@ -87,10 +87,10 @@ "execution_count": 4, "metadata": { "papermill": { - "duration": 0.794016, - "end_time": "2020-10-20T07:38:33.936386", + "duration": 0.597843, + "end_time": "2020-10-22T07:37:56.713092", "exception": false, - "start_time": "2020-10-20T07:38:33.142370", + "start_time": "2020-10-22T07:37:56.115249", "status": "completed" }, "tags": [] @@ -107,10 +107,10 @@ "execution_count": 5, "metadata": { "papermill": { - "duration": 0.02949, - "end_time": "2020-10-20T07:38:33.980536", + "duration": 0.024803, + "end_time": "2020-10-22T07:37:56.749344", "exception": false, - "start_time": "2020-10-20T07:38:33.951046", + "start_time": "2020-10-22T07:37:56.724541", "status": "completed" }, "tags": [] @@ -129,10 +129,10 @@ "execution_count": 6, "metadata": { "papermill": { - "duration": 0.108349, - "end_time": "2020-10-20T07:38:34.102052", + "duration": 0.078335, + "end_time": "2020-10-22T07:37:56.837651", "exception": false, - "start_time": "2020-10-20T07:38:33.993703", + "start_time": "2020-10-22T07:37:56.759316", "status": "completed" }, "tags": [] @@ -280,10 +280,10 @@ "cell_type": "markdown", "metadata": { "papermill": { - "duration": 0.007961, - "end_time": "2020-10-20T07:38:34.124356", + "duration": 0.008528, + "end_time": "2020-10-22T07:37:56.855640", "exception": false, - "start_time": "2020-10-20T07:38:34.116395", + "start_time": "2020-10-22T07:37:56.847112", "status": "completed" }, "tags": [] @@ -297,10 +297,10 @@ "execution_count": 7, "metadata": { "papermill": { - "duration": 0.784791, - "end_time": "2020-10-20T07:38:34.915703", + "duration": 29.269064, + "end_time": "2020-10-22T07:38:26.133112", "exception": false, - "start_time": "2020-10-20T07:38:34.130912", + "start_time": "2020-10-22T07:37:56.864048", "status": "completed" }, "tags": [] @@ -317,10 +317,10 @@ "execution_count": 8, "metadata": { "papermill": { - "duration": 0.069935, - "end_time": "2020-10-20T07:38:35.003603", + "duration": 0.05645, + "end_time": "2020-10-22T07:38:26.205885", "exception": false, - "start_time": "2020-10-20T07:38:34.933668", + "start_time": "2020-10-22T07:38:26.149435", "status": "completed" }, "tags": [] @@ -339,10 +339,10 @@ "execution_count": 9, "metadata": { "papermill": { - "duration": 0.627771, - "end_time": "2020-10-20T07:38:35.647579", + "duration": 0.688088, + "end_time": "2020-10-22T07:38:26.905147", "exception": false, - "start_time": "2020-10-20T07:38:35.019808", + "start_time": "2020-10-22T07:38:26.217059", "status": "completed" }, "tags": [] @@ -352,7 +352,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "12877 data points\n" + "12989 data points\n" ] }, { @@ -402,21 +402,21 @@ " <tbody>\n", " <tr>\n", " <th>0</th>\n", - " <td>20201019</td>\n", + " <td>20201021</td>\n", " <td>AK</td>\n", - " <td>12220.0</td>\n", + " <td>12644.0</td>\n", " <td>NaN</td>\n", - " <td>524003.0</td>\n", + " <td>534496.0</td>\n", " <td>NaN</td>\n", " <td>totalTestsViral</td>\n", - " <td>536223.0</td>\n", - " <td>65.0</td>\n", + " <td>547140.0</td>\n", + " <td>41.0</td>\n", " <td>NaN</td>\n", " <td>...</td>\n", - " <td>536223</td>\n", - " <td>0</td>\n", + " <td>547140</td>\n", + " <td>1</td>\n", " <td>0</td>\n", - " <td>69b847e0fe9b05ba3cc485d576949b9ea2f59cfb</td>\n", + " <td>4d2eabde0cdfbe86ede9f58509002a80af61be19</td>\n", " <td>0</td>\n", " <td>0</td>\n", " <td>0</td>\n", @@ -426,21 +426,21 @@ " </tr>\n", " <tr>\n", " <th>1</th>\n", - " <td>20201019</td>\n", + " <td>20201021</td>\n", " <td>AL</td>\n", - " <td>173485.0</td>\n", - " <td>21213.0</td>\n", - " <td>1107828.0</td>\n", + " <td>174528.0</td>\n", + " <td>21512.0</td>\n", + " <td>1120507.0</td>\n", " <td>NaN</td>\n", " <td>totalTestsViral</td>\n", - " <td>1260100.0</td>\n", - " <td>859.0</td>\n", - " <td>19081.0</td>\n", + " <td>1273523.0</td>\n", + " <td>863.0</td>\n", + " <td>19330.0</td>\n", " <td>...</td>\n", - " <td>1281313</td>\n", - " <td>1</td>\n", - " <td>226</td>\n", - " <td>622efeb21f69f1714609d5c58da3fe7fb9562b13</td>\n", + " <td>1295035</td>\n", + " <td>0</td>\n", + " <td>249</td>\n", + " <td>132b6a5489c29acc31311d7a21bf462b2584f59e</td>\n", " <td>0</td>\n", " <td>0</td>\n", " <td>0</td>\n", @@ -455,20 +455,20 @@ ], "text/plain": [ " date state positive probableCases negative pending \\\n", - "0 20201019 AK 12220.0 NaN 524003.0 NaN \n", - "1 20201019 AL 173485.0 21213.0 1107828.0 NaN \n", + "0 20201021 AK 12644.0 NaN 534496.0 NaN \n", + "1 20201021 AL 174528.0 21512.0 1120507.0 NaN \n", "\n", " totalTestResultsSource totalTestResults hospitalizedCurrently \\\n", - "0 totalTestsViral 536223.0 65.0 \n", - "1 totalTestsViral 1260100.0 859.0 \n", + "0 totalTestsViral 547140.0 41.0 \n", + "1 totalTestsViral 1273523.0 863.0 \n", "\n", " hospitalizedCumulative ... posNeg deathIncrease hospitalizedIncrease \\\n", - "0 NaN ... 536223 0 0 \n", - "1 19081.0 ... 1281313 1 226 \n", + "0 NaN ... 547140 1 0 \n", + "1 19330.0 ... 1295035 0 249 \n", "\n", " hash commercialScore \\\n", - "0 69b847e0fe9b05ba3cc485d576949b9ea2f59cfb 0 \n", - "1 622efeb21f69f1714609d5c58da3fe7fb9562b13 0 \n", + "0 4d2eabde0cdfbe86ede9f58509002a80af61be19 0 \n", + "1 132b6a5489c29acc31311d7a21bf462b2584f59e 0 \n", "\n", " negativeRegularScore negativeScore positiveScore score grade \n", "0 0 0 0 0 \n", @@ -508,18 +508,18 @@ "version": "3.7.3" }, "papermill": { - "duration": 11.263281, - "end_time": "2020-10-20T07:38:36.075825", + "duration": 36.497579, + "end_time": "2020-10-22T07:38:27.226206", "environment_variables": {}, "exception": null, - "input_path": "/tmp/m_poq3ob/notebooks/process/download-covidtracking-data.ipynb", + "input_path": "/tmp/apxgwusv/notebooks/process/download-covidtracking-data.ipynb", "output_path": "runs/download-covidtracking-data.runs.ipynb", "parameters": { - "PAPERMILL_INPUT_PATH": "/tmp/m_poq3ob/notebooks/process/download-covidtracking-data.ipynb", + "PAPERMILL_INPUT_PATH": "/tmp/apxgwusv/notebooks/process/download-covidtracking-data.ipynb", "PAPERMILL_OUTPUT_PATH": "runs/download-covidtracking-data.runs.ipynb", "out_folder": "data/covidtracking" }, - "start_time": "2020-10-20T07:38:24.812544", + "start_time": "2020-10-22T07:37:50.728627", "version": "1.1.0" } }, -- GitLab