From 06ef64ff3b272a554f8aa867a6cbb98aea66314e Mon Sep 17 00:00:00 2001 From: "CR (covid cron)" <beepbop@example.com> Date: Mon, 13 Jul 2020 07:30:10 +0000 Subject: [PATCH] renku rerun data/covidtracking/states-metadata.json data/covidtracking/states-daily.json --- .../fa40d0c1c84b401196713f9c9a9b6df1.cwl | 120 +++++++++++++++++ data/covidtracking/states-daily.json | 4 +- data/covidtracking/states-metadata.json | 4 +- runs/download-covidtracking-data.runs.ipynb | 124 +++++++++--------- 4 files changed, 186 insertions(+), 66 deletions(-) create mode 100644 .renku/workflow/fa40d0c1c84b401196713f9c9a9b6df1.cwl diff --git a/.renku/workflow/fa40d0c1c84b401196713f9c9a9b6df1.cwl b/.renku/workflow/fa40d0c1c84b401196713f9c9a9b6df1.cwl new file mode 100644 index 000000000..8995f2c45 --- /dev/null +++ b/.renku/workflow/fa40d0c1c84b401196713f9c9a9b6df1.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_2: + outputSource: step_1/output_0 + streamable: false + type: File + output_3: + outputSource: step_1/output_1 + streamable: false + type: Directory +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 6fd81809d..55def8128 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 sha256:73f61de66cd2a15ff2e0ceb296815adc2ccc34ba973b280ec56f866b5acce74a -size 6660991 +oid sha256:51188c6706bb3e37906342960c7886cfe237c7e4386c6154a641bff53471203d +size 6713509 diff --git a/data/covidtracking/states-metadata.json b/data/covidtracking/states-metadata.json index 003861938..cdc86b0d4 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:f6759b0ee0af9fedc9c0124f35b03ffd59cf4daaa247ac886a03e9c64fcf4f5a -size 48564 +oid sha256:f2a56259b08d4681dc06622daf80beb5c233166cae41a97dcfbe6d87fe7068ce +size 48663 diff --git a/runs/download-covidtracking-data.runs.ipynb b/runs/download-covidtracking-data.runs.ipynb index d8f259e71..40ee45174 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": 1.253125, - "end_time": "2020-07-12T07:30:09.585051", + "duration": 4.780722, + "end_time": "2020-07-13T07:30:09.120646", "exception": false, - "start_time": "2020-07-12T07:30:08.331926", + "start_time": "2020-07-13T07:30:04.339924", "status": "completed" }, "tags": [] @@ -25,10 +25,10 @@ "execution_count": 2, "metadata": { "papermill": { - "duration": 0.022579, - "end_time": "2020-07-12T07:30:09.621097", + "duration": 0.018573, + "end_time": "2020-07-13T07:30:09.151957", "exception": false, - "start_time": "2020-07-12T07:30:09.598518", + "start_time": "2020-07-13T07:30:09.133384", "status": "completed" }, "tags": [ @@ -46,10 +46,10 @@ "execution_count": 3, "metadata": { "papermill": { - "duration": 0.021159, - "end_time": "2020-07-12T07:30:09.650361", + "duration": 0.020336, + "end_time": "2020-07-13T07:30:09.180856", "exception": false, - "start_time": "2020-07-12T07:30:09.629202", + "start_time": "2020-07-13T07:30:09.160520", "status": "completed" }, "tags": [ @@ -59,7 +59,7 @@ "outputs": [], "source": [ "# Parameters\n", - "PAPERMILL_INPUT_PATH = \"/tmp/sy1d927i/notebooks/process/download-covidtracking-data.ipynb\"\n", + "PAPERMILL_INPUT_PATH = \"/tmp/to3ihk72/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": 0.006997, - "end_time": "2020-07-12T07:30:09.664982", + "duration": 0.008035, + "end_time": "2020-07-13T07:30:09.198082", "exception": false, - "start_time": "2020-07-12T07:30:09.657985", + "start_time": "2020-07-13T07:30:09.190047", "status": "completed" }, "tags": [] @@ -87,10 +87,10 @@ "execution_count": 4, "metadata": { "papermill": { - "duration": 4.639997, - "end_time": "2020-07-12T07:30:14.310806", + "duration": 0.099326, + "end_time": "2020-07-13T07:30:09.305690", "exception": false, - "start_time": "2020-07-12T07:30:09.670809", + "start_time": "2020-07-13T07:30:09.206364", "status": "completed" }, "tags": [] @@ -107,10 +107,10 @@ "execution_count": 5, "metadata": { "papermill": { - "duration": 0.030799, - "end_time": "2020-07-12T07:30:14.355583", + "duration": 0.020007, + "end_time": "2020-07-13T07:30:09.337139", "exception": false, - "start_time": "2020-07-12T07:30:14.324784", + "start_time": "2020-07-13T07:30:09.317132", "status": "completed" }, "tags": [] @@ -129,10 +129,10 @@ "execution_count": 6, "metadata": { "papermill": { - "duration": 0.05518, - "end_time": "2020-07-12T07:30:14.424858", + "duration": 0.068403, + "end_time": "2020-07-13T07:30:09.415513", "exception": false, - "start_time": "2020-07-12T07:30:14.369678", + "start_time": "2020-07-13T07:30:09.347110", "status": "completed" }, "tags": [] @@ -249,10 +249,10 @@ "cell_type": "markdown", "metadata": { "papermill": { - "duration": 0.00736, - "end_time": "2020-07-12T07:30:14.443222", + "duration": 0.00806, + "end_time": "2020-07-13T07:30:09.432548", "exception": false, - "start_time": "2020-07-12T07:30:14.435862", + "start_time": "2020-07-13T07:30:09.424488", "status": "completed" }, "tags": [] @@ -266,10 +266,10 @@ "execution_count": 7, "metadata": { "papermill": { - "duration": 0.248125, - "end_time": "2020-07-12T07:30:14.698024", + "duration": 0.304093, + "end_time": "2020-07-13T07:30:09.744820", "exception": false, - "start_time": "2020-07-12T07:30:14.449899", + "start_time": "2020-07-13T07:30:09.440727", "status": "completed" }, "tags": [] @@ -286,10 +286,10 @@ "execution_count": 8, "metadata": { "papermill": { - "duration": 0.038102, - "end_time": "2020-07-12T07:30:14.752660", + "duration": 0.030586, + "end_time": "2020-07-13T07:30:09.788075", "exception": false, - "start_time": "2020-07-12T07:30:14.714558", + "start_time": "2020-07-13T07:30:09.757489", "status": "completed" }, "tags": [] @@ -308,10 +308,10 @@ "execution_count": 9, "metadata": { "papermill": { - "duration": 0.302876, - "end_time": "2020-07-12T07:30:15.071285", + "duration": 0.324677, + "end_time": "2020-07-13T07:30:10.125728", "exception": false, - "start_time": "2020-07-12T07:30:14.768409", + "start_time": "2020-07-13T07:30:09.801051", "status": "completed" }, "tags": [] @@ -321,7 +321,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "7185 data points\n" + "7241 data points\n" ] }, { @@ -371,21 +371,21 @@ " <tbody>\n", " <tr>\n", " <th>0</th>\n", - " <td>20200711</td>\n", + " <td>20200712</td>\n", " <td>AK</td>\n", - " <td>1385.0</td>\n", - " <td>141991.0</td>\n", + " <td>1479.0</td>\n", + " <td>143996.0</td>\n", " <td>NaN</td>\n", - " <td>31.0</td>\n", + " <td>27.0</td>\n", " <td>NaN</td>\n", " <td>NaN</td>\n", " <td>NaN</td>\n", - " <td>1.0</td>\n", + " <td>0.0</td>\n", " <td>...</td>\n", - " <td>143376</td>\n", + " <td>145475</td>\n", " <td>0</td>\n", " <td>0</td>\n", - " <td>d88f70b7bfa373ef0fb14998ccb0d0d3a9c806fb</td>\n", + " <td>a0d3d26cd6bfe23ff076e92f50acd2e1ee43cfc4</td>\n", " <td>0</td>\n", " <td>0</td>\n", " <td>0</td>\n", @@ -395,21 +395,21 @@ " </tr>\n", " <tr>\n", " <th>1</th>\n", - " <td>20200711</td>\n", + " <td>20200712</td>\n", " <td>AL</td>\n", - " <td>51947.0</td>\n", - " <td>450073.0</td>\n", + " <td>53587.0</td>\n", + " <td>457919.0</td>\n", " <td>NaN</td>\n", " <td>1068.0</td>\n", " <td>6745.0</td>\n", " <td>NaN</td>\n", - " <td>904.0</td>\n", + " <td>911.0</td>\n", " <td>NaN</td>\n", " <td>...</td>\n", - " <td>502020</td>\n", - " <td>10</td>\n", - " <td>3656</td>\n", - " <td>d4bd3a01be0c8af28a542861a4de75cf38649a10</td>\n", + " <td>511506</td>\n", + " <td>7</td>\n", + " <td>0</td>\n", + " <td>fb4327f63eb6b270a2ead2bbdd438615bb7c361f</td>\n", " <td>0</td>\n", " <td>0</td>\n", " <td>0</td>\n", @@ -424,20 +424,20 @@ ], "text/plain": [ " date state positive negative pending hospitalizedCurrently \\\n", - "0 20200711 AK 1385.0 141991.0 NaN 31.0 \n", - "1 20200711 AL 51947.0 450073.0 NaN 1068.0 \n", + "0 20200712 AK 1479.0 143996.0 NaN 27.0 \n", + "1 20200712 AL 53587.0 457919.0 NaN 1068.0 \n", "\n", " hospitalizedCumulative inIcuCurrently inIcuCumulative \\\n", "0 NaN NaN NaN \n", - "1 6745.0 NaN 904.0 \n", + "1 6745.0 NaN 911.0 \n", "\n", " onVentilatorCurrently ... posNeg deathIncrease hospitalizedIncrease \\\n", - "0 1.0 ... 143376 0 0 \n", - "1 NaN ... 502020 10 3656 \n", + "0 0.0 ... 145475 0 0 \n", + "1 NaN ... 511506 7 0 \n", "\n", " hash commercialScore \\\n", - "0 d88f70b7bfa373ef0fb14998ccb0d0d3a9c806fb 0 \n", - "1 d4bd3a01be0c8af28a542861a4de75cf38649a10 0 \n", + "0 a0d3d26cd6bfe23ff076e92f50acd2e1ee43cfc4 0 \n", + "1 fb4327f63eb6b270a2ead2bbdd438615bb7c361f 0 \n", "\n", " negativeRegularScore negativeScore positiveScore score grade \n", "0 0 0 0 0 \n", @@ -477,18 +477,18 @@ "version": "3.7.3" }, "papermill": { - "duration": 8.131372, - "end_time": "2020-07-12T07:30:15.397599", + "duration": 9.487183, + "end_time": "2020-07-13T07:30:10.445396", "environment_variables": {}, "exception": null, - "input_path": "/tmp/sy1d927i/notebooks/process/download-covidtracking-data.ipynb", + "input_path": "/tmp/to3ihk72/notebooks/process/download-covidtracking-data.ipynb", "output_path": "runs/download-covidtracking-data.runs.ipynb", "parameters": { - "PAPERMILL_INPUT_PATH": "/tmp/sy1d927i/notebooks/process/download-covidtracking-data.ipynb", + "PAPERMILL_INPUT_PATH": "/tmp/to3ihk72/notebooks/process/download-covidtracking-data.ipynb", "PAPERMILL_OUTPUT_PATH": "runs/download-covidtracking-data.runs.ipynb", "out_folder": "data/covidtracking" }, - "start_time": "2020-07-12T07:30:07.266227", + "start_time": "2020-07-13T07:30:00.958213", "version": "1.1.0" } }, -- GitLab