diff --git a/.renku/workflow/88764c64ec20413f9fe790b1dfd1dd87.cwl b/.renku/workflow/88764c64ec20413f9fe790b1dfd1dd87.cwl new file mode 100644 index 0000000000000000000000000000000000000000..cacd35c4a592c048d98a6ecf615ea774ca905c47 --- /dev/null +++ b/.renku/workflow/88764c64ec20413f9fe790b1dfd1dd87.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: 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-daily.json + streamable: false + type: string +outputs: + output_0: + outputSource: step_2/output_0 + streamable: false + type: File + output_1: + 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-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: + 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-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: [] diff --git a/data/covidtracking/states-daily.json b/data/covidtracking/states-daily.json index 6233cbf3a78a4505d6b847484014f515fdcd2f38..71f4aed23cdbb041211dbdef016bb654508d640e 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:e6086cb19690e6a1a340496a347395b5659b0d571e797e56fe75f22382cfe0de -size 18253505 +oid sha256:621c2db64408ecf998235e836a602f6c6a428267262c19563696f02874c0d98d +size 18350031 diff --git a/data/covidtracking/states-metadata.json b/data/covidtracking/states-metadata.json index 531ba2ba232bcb533d06058af5477d1d5d9f08a1..22c5f5f3c2d6c09aca2c88e8cb5051aa673b90dd 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 sha256:2a42c427de85fd5f0b2dca4993f4ec06a324f092e0b703bcded87c50defc65b7 -size 104080 +oid sha256:a90c02b00607993b7b37368d4e79437d9d58b24ed000a36668e4fe39d718def8 +size 107425 diff --git a/runs/download-covidtracking-data.runs.ipynb b/runs/download-covidtracking-data.runs.ipynb index 38226a095b7648d1ba32e851fa06d24c436d1617..8f5a19e97b24ebd7cc76379cfd36f9c007ea79ea 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": 4.537249, - "end_time": "2020-10-29T07:39:06.222092", + "duration": 4.322888, + "end_time": "2020-10-30T07:38:40.349844", "exception": false, - "start_time": "2020-10-29T07:39:01.684843", + "start_time": "2020-10-30T07:38:36.026956", "status": "completed" }, "tags": [] @@ -25,10 +25,10 @@ "execution_count": 2, "metadata": { "papermill": { - "duration": 0.021881, - "end_time": "2020-10-29T07:39:06.258241", + "duration": 0.021903, + "end_time": "2020-10-30T07:38:40.384648", "exception": false, - "start_time": "2020-10-29T07:39:06.236360", + "start_time": "2020-10-30T07:38:40.362745", "status": "completed" }, "tags": [ @@ -46,10 +46,10 @@ "execution_count": 3, "metadata": { "papermill": { - "duration": 0.027575, - "end_time": "2020-10-29T07:39:06.297922", + "duration": 0.022912, + "end_time": "2020-10-30T07:38:40.415858", "exception": false, - "start_time": "2020-10-29T07:39:06.270347", + "start_time": "2020-10-30T07:38:40.392946", "status": "completed" }, "tags": [ @@ -59,7 +59,7 @@ "outputs": [], "source": [ "# Parameters\n", - "PAPERMILL_INPUT_PATH = \"/tmp/42lwuooh/notebooks/process/download-covidtracking-data.ipynb\"\n", + "PAPERMILL_INPUT_PATH = \"/tmp/it23r6lx/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": 0.007823, - "end_time": "2020-10-29T07:39:06.317748", + "duration": 0.008181, + "end_time": "2020-10-30T07:38:40.434413", "exception": false, - "start_time": "2020-10-29T07:39:06.309925", + "start_time": "2020-10-30T07:38:40.426232", "status": "completed" }, "tags": [] @@ -87,10 +87,10 @@ "execution_count": 4, "metadata": { "papermill": { - "duration": 0.384563, - "end_time": "2020-10-29T07:39:06.710425", + "duration": 0.570667, + "end_time": "2020-10-30T07:38:41.013127", "exception": false, - "start_time": "2020-10-29T07:39:06.325862", + "start_time": "2020-10-30T07:38:40.442460", "status": "completed" }, "tags": [] @@ -107,10 +107,10 @@ "execution_count": 5, "metadata": { "papermill": { - "duration": 0.023132, - "end_time": "2020-10-29T07:39:06.744099", + "duration": 0.025008, + "end_time": "2020-10-30T07:38:41.047633", "exception": false, - "start_time": "2020-10-29T07:39:06.720967", + "start_time": "2020-10-30T07:38:41.022625", "status": "completed" }, "tags": [] @@ -129,10 +129,10 @@ "execution_count": 6, "metadata": { "papermill": { - "duration": 0.110546, - "end_time": "2020-10-29T07:39:06.864298", + "duration": 0.077261, + "end_time": "2020-10-30T07:38:41.133806", "exception": false, - "start_time": "2020-10-29T07:39:06.753752", + "start_time": "2020-10-30T07:38:41.056545", "status": "completed" }, "tags": [] @@ -280,10 +280,10 @@ "cell_type": "markdown", "metadata": { "papermill": { - "duration": 0.009476, - "end_time": "2020-10-29T07:39:06.883639", + "duration": 0.008744, + "end_time": "2020-10-30T07:38:41.155983", "exception": false, - "start_time": "2020-10-29T07:39:06.874163", + "start_time": "2020-10-30T07:38:41.147239", "status": "completed" }, "tags": [] @@ -297,10 +297,10 @@ "execution_count": 7, "metadata": { "papermill": { - "duration": 30.429905, - "end_time": "2020-10-29T07:39:37.322953", + "duration": 30.457404, + "end_time": "2020-10-30T07:39:11.621966", "exception": false, - "start_time": "2020-10-29T07:39:06.893048", + "start_time": "2020-10-30T07:38:41.164562", "status": "completed" }, "tags": [] @@ -317,10 +317,10 @@ "execution_count": 8, "metadata": { "papermill": { - "duration": 0.053599, - "end_time": "2020-10-29T07:39:37.390618", + "duration": 0.053966, + "end_time": "2020-10-30T07:39:11.689178", "exception": false, - "start_time": "2020-10-29T07:39:37.337019", + "start_time": "2020-10-30T07:39:11.635212", "status": "completed" }, "tags": [] @@ -339,10 +339,10 @@ "execution_count": 9, "metadata": { "papermill": { - "duration": 0.701681, - "end_time": "2020-10-29T07:39:38.103517", + "duration": 0.692648, + "end_time": "2020-10-30T07:39:12.392023", "exception": false, - "start_time": "2020-10-29T07:39:37.401836", + "start_time": "2020-10-30T07:39:11.699375", "status": "completed" }, "tags": [] @@ -352,7 +352,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "13416 data points\n" + "13476 data points\n" ] }, { @@ -402,21 +402,21 @@ " <tbody>\n", " <tr>\n", " <th>0</th>\n", - " <td>20201028</td>\n", + " <td>20201029</td>\n", " <td>AK</td>\n", - " <td>15155.0</td>\n", + " <td>15522.0</td>\n", " <td>NaN</td>\n", - " <td>565444.0</td>\n", + " <td>568746.0</td>\n", " <td>NaN</td>\n", " <td>totalTestsViral</td>\n", - " <td>580599.0</td>\n", - " <td>80.0</td>\n", + " <td>584268.0</td>\n", + " <td>89.0</td>\n", " <td>NaN</td>\n", " <td>...</td>\n", - " <td>580599</td>\n", - " <td>1</td>\n", + " <td>584268</td>\n", + " <td>6</td>\n", " <td>0</td>\n", - " <td>f0f48cae1ff48cce0b1dfa2a67c30709261bf7f5</td>\n", + " <td>01d32bd4e56cdbdb3ce1f28f13f4d195e46fc6af</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>20201028</td>\n", + " <td>20201029</td>\n", " <td>AL</td>\n", - " <td>187706.0</td>\n", - " <td>27326.0</td>\n", - " <td>1159926.0</td>\n", + " <td>189149.0</td>\n", + " <td>27612.0</td>\n", + " <td>1165898.0</td>\n", " <td>NaN</td>\n", " <td>totalTestsViral</td>\n", - " <td>1320306.0</td>\n", + " <td>1327435.0</td>\n", " <td>1013.0</td>\n", - " <td>20116.0</td>\n", + " <td>20246.0</td>\n", " <td>...</td>\n", - " <td>1347632</td>\n", - " <td>19</td>\n", - " <td>142</td>\n", - " <td>c713ea2c14a2c1435e7c7cbada7a09af31a376a6</td>\n", + " <td>1355047</td>\n", + " <td>3</td>\n", + " <td>130</td>\n", + " <td>cbe87bb193799153fdc2dd806e04fe810f982227</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 20201028 AK 15155.0 NaN 565444.0 NaN \n", - "1 20201028 AL 187706.0 27326.0 1159926.0 NaN \n", + "0 20201029 AK 15522.0 NaN 568746.0 NaN \n", + "1 20201029 AL 189149.0 27612.0 1165898.0 NaN \n", "\n", " totalTestResultsSource totalTestResults hospitalizedCurrently \\\n", - "0 totalTestsViral 580599.0 80.0 \n", - "1 totalTestsViral 1320306.0 1013.0 \n", + "0 totalTestsViral 584268.0 89.0 \n", + "1 totalTestsViral 1327435.0 1013.0 \n", "\n", " hospitalizedCumulative ... posNeg deathIncrease hospitalizedIncrease \\\n", - "0 NaN ... 580599 1 0 \n", - "1 20116.0 ... 1347632 19 142 \n", + "0 NaN ... 584268 6 0 \n", + "1 20246.0 ... 1355047 3 130 \n", "\n", " hash commercialScore \\\n", - "0 f0f48cae1ff48cce0b1dfa2a67c30709261bf7f5 0 \n", - "1 c713ea2c14a2c1435e7c7cbada7a09af31a376a6 0 \n", + "0 01d32bd4e56cdbdb3ce1f28f13f4d195e46fc6af 0 \n", + "1 cbe87bb193799153fdc2dd806e04fe810f982227 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": 39.630647, - "end_time": "2020-10-29T07:39:38.423262", + "duration": 38.511335, + "end_time": "2020-10-30T07:39:12.714574", "environment_variables": {}, "exception": null, - "input_path": "/tmp/42lwuooh/notebooks/process/download-covidtracking-data.ipynb", + "input_path": "/tmp/it23r6lx/notebooks/process/download-covidtracking-data.ipynb", "output_path": "runs/download-covidtracking-data.runs.ipynb", "parameters": { - "PAPERMILL_INPUT_PATH": "/tmp/42lwuooh/notebooks/process/download-covidtracking-data.ipynb", + "PAPERMILL_INPUT_PATH": "/tmp/it23r6lx/notebooks/process/download-covidtracking-data.ipynb", "PAPERMILL_OUTPUT_PATH": "runs/download-covidtracking-data.runs.ipynb", "out_folder": "data/covidtracking" }, - "start_time": "2020-10-29T07:38:58.792615", + "start_time": "2020-10-30T07:38:34.203239", "version": "1.1.0" } },