From 4597cd96a8c52ccc007d7402321877b4e9bf9a01 Mon Sep 17 00:00:00 2001 From: "CR (covid cron)" <beepbop@example.com> Date: Fri, 5 Jun 2020 07:26:42 +0000 Subject: [PATCH] renku rerun data/covidtracking/states-metadata.json data/covidtracking/states-daily.json --- .../faf9a75a6e43415bb1c5b9b002e51f78.cwl | 120 +++++++++++++++++ data/covidtracking/states-daily.json | 4 +- data/covidtracking/states-metadata.json | 4 +- runs/download-covidtracking-data.runs.ipynb | 126 +++++++++--------- 4 files changed, 187 insertions(+), 67 deletions(-) create mode 100644 .renku/workflow/faf9a75a6e43415bb1c5b9b002e51f78.cwl diff --git a/.renku/workflow/faf9a75a6e43415bb1c5b9b002e51f78.cwl b/.renku/workflow/faf9a75a6e43415bb1c5b9b002e51f78.cwl new file mode 100644 index 000000000..0c4ffa04b --- /dev/null +++ b/.renku/workflow/faf9a75a6e43415bb1c5b9b002e51f78.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_0: + outputSource: step_3/output_1 + streamable: false + type: Directory + output_2: + outputSource: step_3/output_0 + streamable: false + type: File +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 1f039ac48..3c4b186a3 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 sha256:8cd217cca3afcedb310e36a7ea42508c92271044acc349992bea5abf79a05f6a -size 3940450 +oid sha256:3bd629062dd7df6fbfecb645e2597200da55a411b07f8a3b946a125e47da60a8 +size 3984683 diff --git a/data/covidtracking/states-metadata.json b/data/covidtracking/states-metadata.json index 28ce6ebec..c1e746486 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 sha256:8b0c5cfa8aedded7e57c76535faaa4f2b863b26d50909e984a39bbf6e8a5de59 -size 34797 +oid sha256:c7ab8c45e4de35bc9cf318cf88bc92f858170281fc558ef94f15b0c471e084b2 +size 35112 diff --git a/runs/download-covidtracking-data.runs.ipynb b/runs/download-covidtracking-data.runs.ipynb index 07cba5714..008a705b3 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": 4.627897, - "end_time": "2020-06-04T08:28:04.985732", + "duration": 1.081365, + "end_time": "2020-06-05T07:26:40.376216", "exception": false, - "start_time": "2020-06-04T08:28:00.357835", + "start_time": "2020-06-05T07:26:39.294851", "status": "completed" }, "tags": [] @@ -25,10 +25,10 @@ "execution_count": 2, "metadata": { "papermill": { - "duration": 0.022291, - "end_time": "2020-06-04T08:28:05.020399", + "duration": 0.026604, + "end_time": "2020-06-05T07:26:40.419396", "exception": false, - "start_time": "2020-06-04T08:28:04.998108", + "start_time": "2020-06-05T07:26:40.392792", "status": "completed" }, "tags": [ @@ -46,10 +46,10 @@ "execution_count": 3, "metadata": { "papermill": { - "duration": 0.022545, - "end_time": "2020-06-04T08:28:05.052282", + "duration": 0.023283, + "end_time": "2020-06-05T07:26:40.455880", "exception": false, - "start_time": "2020-06-04T08:28:05.029737", + "start_time": "2020-06-05T07:26:40.432597", "status": "completed" }, "tags": [ @@ -59,7 +59,7 @@ "outputs": [], "source": [ "# Parameters\n", - "PAPERMILL_INPUT_PATH = \"/tmp/m_83rm_4/notebooks/process/download-covidtracking-data.ipynb\"\n", + "PAPERMILL_INPUT_PATH = \"/tmp/nhlov4s_/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": 0.007006, - "end_time": "2020-06-04T08:28:05.068409", + "duration": 0.007144, + "end_time": "2020-06-05T07:26:40.473105", "exception": false, - "start_time": "2020-06-04T08:28:05.061403", + "start_time": "2020-06-05T07:26:40.465961", "status": "completed" }, "tags": [] @@ -87,10 +87,10 @@ "execution_count": 4, "metadata": { "papermill": { - "duration": 0.381514, - "end_time": "2020-06-04T08:28:05.457090", + "duration": 0.174501, + "end_time": "2020-06-05T07:26:40.653764", "exception": false, - "start_time": "2020-06-04T08:28:05.075576", + "start_time": "2020-06-05T07:26:40.479263", "status": "completed" }, "tags": [] @@ -107,10 +107,10 @@ "execution_count": 5, "metadata": { "papermill": { - "duration": 0.027088, - "end_time": "2020-06-04T08:28:05.496958", + "duration": 0.025897, + "end_time": "2020-06-05T07:26:40.695095", "exception": false, - "start_time": "2020-06-04T08:28:05.469870", + "start_time": "2020-06-05T07:26:40.669198", "status": "completed" }, "tags": [] @@ -129,10 +129,10 @@ "execution_count": 6, "metadata": { "papermill": { - "duration": 0.072587, - "end_time": "2020-06-04T08:28:05.580434", + "duration": 0.073474, + "end_time": "2020-06-05T07:26:40.778005", "exception": false, - "start_time": "2020-06-04T08:28:05.507847", + "start_time": "2020-06-05T07:26:40.704531", "status": "completed" }, "tags": [] @@ -242,10 +242,10 @@ "cell_type": "markdown", "metadata": { "papermill": { - "duration": 0.008248, - "end_time": "2020-06-04T08:28:05.598828", + "duration": 0.00772, + "end_time": "2020-06-05T07:26:40.798117", "exception": false, - "start_time": "2020-06-04T08:28:05.590580", + "start_time": "2020-06-05T07:26:40.790397", "status": "completed" }, "tags": [] @@ -259,10 +259,10 @@ "execution_count": 7, "metadata": { "papermill": { - "duration": 0.154111, - "end_time": "2020-06-04T08:28:05.761833", + "duration": 0.209878, + "end_time": "2020-06-05T07:26:41.014535", "exception": false, - "start_time": "2020-06-04T08:28:05.607722", + "start_time": "2020-06-05T07:26:40.804657", "status": "completed" }, "tags": [] @@ -279,10 +279,10 @@ "execution_count": 8, "metadata": { "papermill": { - "duration": 0.029699, - "end_time": "2020-06-04T08:28:05.803127", + "duration": 0.033848, + "end_time": "2020-06-05T07:26:41.066030", "exception": false, - "start_time": "2020-06-04T08:28:05.773428", + "start_time": "2020-06-05T07:26:41.032182", "status": "completed" }, "tags": [] @@ -301,10 +301,10 @@ "execution_count": 9, "metadata": { "papermill": { - "duration": 0.20856, - "end_time": "2020-06-04T08:28:06.022260", + "duration": 0.195065, + "end_time": "2020-06-05T07:26:41.272416", "exception": false, - "start_time": "2020-06-04T08:28:05.813700", + "start_time": "2020-06-05T07:26:41.077351", "status": "completed" }, "tags": [] @@ -314,7 +314,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "5057 data points\n" + "5113 data points\n" ] }, { @@ -364,21 +364,21 @@ " <tbody>\n", " <tr>\n", " <th>0</th>\n", - " <td>20200603</td>\n", + " <td>20200604</td>\n", " <td>AK</td>\n", - " <td>505.0</td>\n", - " <td>57677.0</td>\n", + " <td>513.0</td>\n", + " <td>59584.0</td>\n", " <td>NaN</td>\n", - " <td>11.0</td>\n", + " <td>13.0</td>\n", " <td>NaN</td>\n", " <td>NaN</td>\n", " <td>NaN</td>\n", - " <td>0.0</td>\n", + " <td>1.0</td>\n", " <td>...</td>\n", - " <td>58182</td>\n", + " <td>60097</td>\n", " <td>0</td>\n", " <td>0</td>\n", - " <td>02548c93014e510ca02e0fc92122c299e4aa8e78</td>\n", + " <td>c1046011af7271cbe2e6698526714c6cb5b92748</td>\n", " <td>0</td>\n", " <td>0</td>\n", " <td>0</td>\n", @@ -388,21 +388,21 @@ " </tr>\n", " <tr>\n", " <th>1</th>\n", - " <td>20200603</td>\n", + " <td>20200604</td>\n", " <td>AL</td>\n", - " <td>18851.0</td>\n", - " <td>212743.0</td>\n", + " <td>19072.0</td>\n", + " <td>216227.0</td>\n", " <td>NaN</td>\n", " <td>NaN</td>\n", - " <td>1900.0</td>\n", + " <td>1929.0</td>\n", " <td>NaN</td>\n", - " <td>591.0</td>\n", + " <td>601.0</td>\n", " <td>NaN</td>\n", " <td>...</td>\n", - " <td>231594</td>\n", - " <td>2</td>\n", - " <td>21</td>\n", - " <td>fe5df10e9c8639e15d2ce02d16d678e16f6f6cc7</td>\n", + " <td>235299</td>\n", + " <td>0</td>\n", + " <td>29</td>\n", + " <td>bcbefdb36212ba2b97b5a354f4e45bf16648ee23</td>\n", " <td>0</td>\n", " <td>0</td>\n", " <td>0</td>\n", @@ -417,20 +417,20 @@ ], "text/plain": [ " date state positive negative pending hospitalizedCurrently \\\n", - "0 20200603 AK 505.0 57677.0 NaN 11.0 \n", - "1 20200603 AL 18851.0 212743.0 NaN NaN \n", + "0 20200604 AK 513.0 59584.0 NaN 13.0 \n", + "1 20200604 AL 19072.0 216227.0 NaN NaN \n", "\n", " hospitalizedCumulative inIcuCurrently inIcuCumulative \\\n", "0 NaN NaN NaN \n", - "1 1900.0 NaN 591.0 \n", + "1 1929.0 NaN 601.0 \n", "\n", " onVentilatorCurrently ... posNeg deathIncrease hospitalizedIncrease \\\n", - "0 0.0 ... 58182 0 0 \n", - "1 NaN ... 231594 2 21 \n", + "0 1.0 ... 60097 0 0 \n", + "1 NaN ... 235299 0 29 \n", "\n", " hash commercialScore \\\n", - "0 02548c93014e510ca02e0fc92122c299e4aa8e78 0 \n", - "1 fe5df10e9c8639e15d2ce02d16d678e16f6f6cc7 0 \n", + "0 c1046011af7271cbe2e6698526714c6cb5b92748 0 \n", + "1 bcbefdb36212ba2b97b5a354f4e45bf16648ee23 0 \n", "\n", " negativeRegularScore negativeScore positiveScore score grade \n", "0 0 0 0 0 \n", @@ -470,18 +470,18 @@ "version": "3.7.3" }, "papermill": { - "duration": 7.919109, - "end_time": "2020-06-04T08:28:06.447225", + "duration": 3.349554, + "end_time": "2020-06-05T07:26:41.597056", "environment_variables": {}, "exception": null, - "input_path": "/tmp/m_83rm_4/notebooks/process/download-covidtracking-data.ipynb", + "input_path": "/tmp/nhlov4s_/notebooks/process/download-covidtracking-data.ipynb", "output_path": "runs/download-covidtracking-data.runs.ipynb", "parameters": { - "PAPERMILL_INPUT_PATH": "/tmp/m_83rm_4/notebooks/process/download-covidtracking-data.ipynb", + "PAPERMILL_INPUT_PATH": "/tmp/nhlov4s_/notebooks/process/download-covidtracking-data.ipynb", "PAPERMILL_OUTPUT_PATH": "runs/download-covidtracking-data.runs.ipynb", "out_folder": "data/covidtracking" }, - "start_time": "2020-06-04T08:27:58.528116", + "start_time": "2020-06-05T07:26:38.247502", "version": "1.1.0" } }, -- GitLab