From 4d58c6eb9619b341ad4e12a054c43f3f75b18358 Mon Sep 17 00:00:00 2001 From: "CR (covid cron)" <beepbop@example.com> Date: Fri, 10 Jul 2020 07:30:45 +0000 Subject: [PATCH] renku rerun data/covidtracking/states-metadata.json data/covidtracking/states-daily.json --- .../c8b0e4f875e5472c82f15c37053cbbfd.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/c8b0e4f875e5472c82f15c37053cbbfd.cwl diff --git a/.renku/workflow/c8b0e4f875e5472c82f15c37053cbbfd.cwl b/.renku/workflow/c8b0e4f875e5472c82f15c37053cbbfd.cwl new file mode 100644 index 000000000..5e91f8298 --- /dev/null +++ b/.renku/workflow/c8b0e4f875e5472c82f15c37053cbbfd.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_1 + streamable: false + type: Directory + output_1: + outputSource: step_2/output_0 + streamable: false + type: File +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_0 + - output_1 + 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 6e0b71fd7..03926b5da 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 sha256:6d09adcf8e3867562152154cfb55e909478a0d08382f330dac1875b707a3d4ba -size 6503444 +oid sha256:0f962505bcb6042a186eb3e383907fa325851842d829674dbefd29510a3f97fb +size 6555942 diff --git a/data/covidtracking/states-metadata.json b/data/covidtracking/states-metadata.json index f90ac7340..02c8b6753 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:ed5c9cc4193269f8be2970077387313776ee2405234a830b1e9d0373781e82d9 -size 48068 +oid sha256:5cc91a8c937cfb81a31702bb5fff19ebf56297295ea9b5eca63b414c6ba9fc72 +size 48163 diff --git a/runs/download-covidtracking-data.runs.ipynb b/runs/download-covidtracking-data.runs.ipynb index 19294340c..c208642f8 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": 4.359006, - "end_time": "2020-07-09T07:30:08.774769", + "duration": 4.875701, + "end_time": "2020-07-10T07:30:43.715703", "exception": false, - "start_time": "2020-07-09T07:30:04.415763", + "start_time": "2020-07-10T07:30:38.840002", "status": "completed" }, "tags": [] @@ -25,10 +25,10 @@ "execution_count": 2, "metadata": { "papermill": { - "duration": 0.030327, - "end_time": "2020-07-09T07:30:08.821783", + "duration": 0.017583, + "end_time": "2020-07-10T07:30:43.745704", "exception": false, - "start_time": "2020-07-09T07:30:08.791456", + "start_time": "2020-07-10T07:30:43.728121", "status": "completed" }, "tags": [ @@ -46,10 +46,10 @@ "execution_count": 3, "metadata": { "papermill": { - "duration": 0.023247, - "end_time": "2020-07-09T07:30:08.858730", + "duration": 0.020528, + "end_time": "2020-07-10T07:30:43.773494", "exception": false, - "start_time": "2020-07-09T07:30:08.835483", + "start_time": "2020-07-10T07:30:43.752966", "status": "completed" }, "tags": [ @@ -59,7 +59,7 @@ "outputs": [], "source": [ "# Parameters\n", - "PAPERMILL_INPUT_PATH = \"/tmp/7998tnm6/notebooks/process/download-covidtracking-data.ipynb\"\n", + "PAPERMILL_INPUT_PATH = \"/tmp/zozi8wxi/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": 0.006754, - "end_time": "2020-07-09T07:30:08.876050", + "duration": 0.007995, + "end_time": "2020-07-10T07:30:43.790951", "exception": false, - "start_time": "2020-07-09T07:30:08.869296", + "start_time": "2020-07-10T07:30:43.782956", "status": "completed" }, "tags": [] @@ -87,10 +87,10 @@ "execution_count": 4, "metadata": { "papermill": { - "duration": 0.185863, - "end_time": "2020-07-09T07:30:09.068324", + "duration": 0.076221, + "end_time": "2020-07-10T07:30:43.874352", "exception": false, - "start_time": "2020-07-09T07:30:08.882461", + "start_time": "2020-07-10T07:30:43.798131", "status": "completed" }, "tags": [] @@ -107,10 +107,10 @@ "execution_count": 5, "metadata": { "papermill": { - "duration": 0.025901, - "end_time": "2020-07-09T07:30:09.109237", + "duration": 0.021758, + "end_time": "2020-07-10T07:30:43.905004", "exception": false, - "start_time": "2020-07-09T07:30:09.083336", + "start_time": "2020-07-10T07:30:43.883246", "status": "completed" }, "tags": [] @@ -129,10 +129,10 @@ "execution_count": 6, "metadata": { "papermill": { - "duration": 0.078569, - "end_time": "2020-07-09T07:30:09.197037", + "duration": 0.069709, + "end_time": "2020-07-10T07:30:43.983224", "exception": false, - "start_time": "2020-07-09T07:30:09.118468", + "start_time": "2020-07-10T07:30:43.913515", "status": "completed" }, "tags": [] @@ -249,10 +249,10 @@ "cell_type": "markdown", "metadata": { "papermill": { - "duration": 0.007765, - "end_time": "2020-07-09T07:30:09.217117", + "duration": 0.008943, + "end_time": "2020-07-10T07:30:44.001150", "exception": false, - "start_time": "2020-07-09T07:30:09.209352", + "start_time": "2020-07-10T07:30:43.992207", "status": "completed" }, "tags": [] @@ -266,10 +266,10 @@ "execution_count": 7, "metadata": { "papermill": { - "duration": 0.244587, - "end_time": "2020-07-09T07:30:09.468401", + "duration": 0.227183, + "end_time": "2020-07-10T07:30:44.236566", "exception": false, - "start_time": "2020-07-09T07:30:09.223814", + "start_time": "2020-07-10T07:30:44.009383", "status": "completed" }, "tags": [] @@ -286,10 +286,10 @@ "execution_count": 8, "metadata": { "papermill": { - "duration": 0.027661, - "end_time": "2020-07-09T07:30:09.515243", + "duration": 0.029433, + "end_time": "2020-07-10T07:30:44.278153", "exception": false, - "start_time": "2020-07-09T07:30:09.487582", + "start_time": "2020-07-10T07:30:44.248720", "status": "completed" }, "tags": [] @@ -308,10 +308,10 @@ "execution_count": 9, "metadata": { "papermill": { - "duration": 0.30228, - "end_time": "2020-07-09T07:30:09.828236", + "duration": 0.311198, + "end_time": "2020-07-10T07:30:44.600669", "exception": false, - "start_time": "2020-07-09T07:30:09.525956", + "start_time": "2020-07-10T07:30:44.289471", "status": "completed" }, "tags": [] @@ -321,7 +321,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "7017 data points\n" + "7073 data points\n" ] }, { @@ -371,21 +371,21 @@ " <tbody>\n", " <tr>\n", " <th>0</th>\n", - " <td>20200708</td>\n", + " <td>20200709</td>\n", " <td>AK</td>\n", - " <td>1226.0</td>\n", - " <td>132175.0</td>\n", + " <td>1272.0</td>\n", + " <td>134472.0</td>\n", " <td>NaN</td>\n", - " <td>30.0</td>\n", + " <td>28.0</td>\n", " <td>NaN</td>\n", " <td>NaN</td>\n", " <td>NaN</td>\n", " <td>0.0</td>\n", " <td>...</td>\n", - " <td>133401</td>\n", + " <td>135744</td>\n", " <td>0</td>\n", " <td>0</td>\n", - " <td>44f40820165a4480d4a1b8b031bb7e6bf3a22a40</td>\n", + " <td>55912ff71f785e526d4154c6ddd12b7188f17807</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>20200708</td>\n", + " <td>20200709</td>\n", " <td>AL</td>\n", - " <td>46962.0</td>\n", + " <td>49174.0</td>\n", " <td>421330.0</td>\n", " <td>NaN</td>\n", - " <td>1110.0</td>\n", - " <td>3006.0</td>\n", + " <td>1125.0</td>\n", + " <td>3039.0</td>\n", " <td>NaN</td>\n", - " <td>871.0</td>\n", + " <td>877.0</td>\n", " <td>NaN</td>\n", " <td>...</td>\n", - " <td>468292</td>\n", - " <td>25</td>\n", - " <td>45</td>\n", - " <td>9fc63c874a98fa97cfee6a65d2dff374513b499f</td>\n", + " <td>470504</td>\n", + " <td>10</td>\n", + " <td>33</td>\n", + " <td>ce6e123b52713c8777e9a0b9e97cc7253918fb4a</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 20200708 AK 1226.0 132175.0 NaN 30.0 \n", - "1 20200708 AL 46962.0 421330.0 NaN 1110.0 \n", + "0 20200709 AK 1272.0 134472.0 NaN 28.0 \n", + "1 20200709 AL 49174.0 421330.0 NaN 1125.0 \n", "\n", " hospitalizedCumulative inIcuCurrently inIcuCumulative \\\n", "0 NaN NaN NaN \n", - "1 3006.0 NaN 871.0 \n", + "1 3039.0 NaN 877.0 \n", "\n", " onVentilatorCurrently ... posNeg deathIncrease hospitalizedIncrease \\\n", - "0 0.0 ... 133401 0 0 \n", - "1 NaN ... 468292 25 45 \n", + "0 0.0 ... 135744 0 0 \n", + "1 NaN ... 470504 10 33 \n", "\n", " hash commercialScore \\\n", - "0 44f40820165a4480d4a1b8b031bb7e6bf3a22a40 0 \n", - "1 9fc63c874a98fa97cfee6a65d2dff374513b499f 0 \n", + "0 55912ff71f785e526d4154c6ddd12b7188f17807 0 \n", + "1 ce6e123b52713c8777e9a0b9e97cc7253918fb4a 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": 8.238482, - "end_time": "2020-07-09T07:30:10.254946", + "duration": 8.399002, + "end_time": "2020-07-10T07:30:44.935352", "environment_variables": {}, "exception": null, - "input_path": "/tmp/7998tnm6/notebooks/process/download-covidtracking-data.ipynb", + "input_path": "/tmp/zozi8wxi/notebooks/process/download-covidtracking-data.ipynb", "output_path": "runs/download-covidtracking-data.runs.ipynb", "parameters": { - "PAPERMILL_INPUT_PATH": "/tmp/7998tnm6/notebooks/process/download-covidtracking-data.ipynb", + "PAPERMILL_INPUT_PATH": "/tmp/zozi8wxi/notebooks/process/download-covidtracking-data.ipynb", "PAPERMILL_OUTPUT_PATH": "runs/download-covidtracking-data.runs.ipynb", "out_folder": "data/covidtracking" }, - "start_time": "2020-07-09T07:30:02.016464", + "start_time": "2020-07-10T07:30:36.536350", "version": "1.1.0" } }, -- GitLab