diff --git a/.renku/workflow/e25674859ffe42549abfa4d7c1dcfc7b.cwl b/.renku/workflow/e25674859ffe42549abfa4d7c1dcfc7b.cwl new file mode 100644 index 0000000000000000000000000000000000000000..865b8e8feae91b1c7b3d964261dd582d897ea421 --- /dev/null +++ b/.renku/workflow/e25674859ffe42549abfa4d7c1dcfc7b.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-metadata.json + streamable: false + type: string + input_6: + default: states-daily.json + streamable: false + type: string +outputs: + output_1: + outputSource: step_1/output_1 + streamable: false + type: Directory + output_3: + outputSource: step_1/output_0 + streamable: false + type: File +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-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_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-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 d8bf3a130ebae67ffc01a7952ab7c870aa8ffd59..27dfd82d2a76732f2a0bf6c291926c933d1944c2 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 sha256:2ed9e011d2eee5b892662c6ac60fa8dc40c81e35db6702d0f0caf6a8891530b6 -size 2806544 +oid sha256:b53d5ec861e859d9c4b5d92c824a94cf34fccdc411feee3fe450ca1b3566e6aa +size 2945856 diff --git a/data/covidtracking/states-metadata.json b/data/covidtracking/states-metadata.json index f7c2f3a122f7891344445fdc6eb99876f99b3a28..095f192b9ce6cf9f53c642a5b9c7516e9050cf4e 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 sha256:006c2bec36b15b3b02750aa6b4f65f2b58c03ef27674bbc7bac7bdf547caf00b -size 34988 +oid sha256:23628a019bf4b14d081e8b8519be4be9ee4712078cae76e8f455f72c066ffb9c +size 35330 diff --git a/runs/download-covidtracking-data.runs.ipynb b/runs/download-covidtracking-data.runs.ipynb index 5de27e17d3d95b41a503b37e9c903d98a6a5af52..2bbab0ab4fd1eaa30698e8babf1489f14b23ab02 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": 3.237693, - "end_time": "2020-05-29T07:27:31.480700", + "duration": 0.52214, + "end_time": "2020-06-02T08:11:09.503843", "exception": false, - "start_time": "2020-05-29T07:27:28.243007", + "start_time": "2020-06-02T08:11:08.981703", "status": "completed" }, "tags": [] @@ -25,10 +25,10 @@ "execution_count": 2, "metadata": { "papermill": { - "duration": 0.019555, - "end_time": "2020-05-29T07:27:31.511133", + "duration": 0.021722, + "end_time": "2020-06-02T08:11:09.539612", "exception": false, - "start_time": "2020-05-29T07:27:31.491578", + "start_time": "2020-06-02T08:11:09.517890", "status": "completed" }, "tags": [ @@ -46,10 +46,10 @@ "execution_count": 3, "metadata": { "papermill": { - "duration": 0.019505, - "end_time": "2020-05-29T07:27:31.542455", + "duration": 0.022346, + "end_time": "2020-06-02T08:11:09.570298", "exception": false, - "start_time": "2020-05-29T07:27:31.522950", + "start_time": "2020-06-02T08:11:09.547952", "status": "completed" }, "tags": [ @@ -59,7 +59,7 @@ "outputs": [], "source": [ "# Parameters\n", - "PAPERMILL_INPUT_PATH = \"/tmp/8w_tcx45/notebooks/process/download-covidtracking-data.ipynb\"\n", + "PAPERMILL_INPUT_PATH = \"/tmp/_29it5g5/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": 0.008692, - "end_time": "2020-05-29T07:27:31.565346", + "duration": 0.006388, + "end_time": "2020-06-02T08:11:09.585324", "exception": false, - "start_time": "2020-05-29T07:27:31.556654", + "start_time": "2020-06-02T08:11:09.578936", "status": "completed" }, "tags": [] @@ -87,10 +87,10 @@ "execution_count": 4, "metadata": { "papermill": { - "duration": 0.72501, - "end_time": "2020-05-29T07:27:32.299043", + "duration": 0.620735, + "end_time": "2020-06-02T08:11:10.212779", "exception": false, - "start_time": "2020-05-29T07:27:31.574033", + "start_time": "2020-06-02T08:11:09.592044", "status": "completed" }, "tags": [] @@ -107,10 +107,10 @@ "execution_count": 5, "metadata": { "papermill": { - "duration": 0.021449, - "end_time": "2020-05-29T07:27:32.330516", + "duration": 0.028753, + "end_time": "2020-06-02T08:11:10.257183", "exception": false, - "start_time": "2020-05-29T07:27:32.309067", + "start_time": "2020-06-02T08:11:10.228430", "status": "completed" }, "tags": [] @@ -129,10 +129,10 @@ "execution_count": 6, "metadata": { "papermill": { - "duration": 0.074782, - "end_time": "2020-05-29T07:27:32.415415", + "duration": 0.048608, + "end_time": "2020-06-02T08:11:10.315976", "exception": false, - "start_time": "2020-05-29T07:27:32.340633", + "start_time": "2020-06-02T08:11:10.267368", "status": "completed" }, "tags": [] @@ -246,10 +246,10 @@ "cell_type": "markdown", "metadata": { "papermill": { - "duration": 0.007798, - "end_time": "2020-05-29T07:27:32.434642", + "duration": 0.00642, + "end_time": "2020-06-02T08:11:10.329275", "exception": false, - "start_time": "2020-05-29T07:27:32.426844", + "start_time": "2020-06-02T08:11:10.322855", "status": "completed" }, "tags": [] @@ -263,10 +263,10 @@ "execution_count": 7, "metadata": { "papermill": { - "duration": 5.079992, - "end_time": "2020-05-29T07:27:37.522708", + "duration": 5.270376, + "end_time": "2020-06-02T08:11:15.606304", "exception": false, - "start_time": "2020-05-29T07:27:32.442716", + "start_time": "2020-06-02T08:11:10.335928", "status": "completed" }, "tags": [] @@ -283,10 +283,10 @@ "execution_count": 8, "metadata": { "papermill": { - "duration": 0.03146, - "end_time": "2020-05-29T07:27:37.568666", + "duration": 0.033573, + "end_time": "2020-06-02T08:11:15.657902", "exception": false, - "start_time": "2020-05-29T07:27:37.537206", + "start_time": "2020-06-02T08:11:15.624329", "status": "completed" }, "tags": [] @@ -305,10 +305,10 @@ "execution_count": 9, "metadata": { "papermill": { - "duration": 0.1763, - "end_time": "2020-05-29T07:27:37.756153", + "duration": 0.157194, + "end_time": "2020-06-02T08:11:15.830240", "exception": false, - "start_time": "2020-05-29T07:27:37.579853", + "start_time": "2020-06-02T08:11:15.673046", "status": "completed" }, "tags": [] @@ -318,7 +318,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "4721 data points\n" + "4945 data points\n" ] }, { @@ -368,51 +368,51 @@ " <tbody>\n", " <tr>\n", " <th>0</th>\n", - " <td>20200528</td>\n", + " <td>20200601</td>\n", " <td>AK</td>\n", - " <td>425.0</td>\n", - " <td>47545.0</td>\n", + " <td>467.0</td>\n", + " <td>53723.0</td>\n", " <td>NaN</td>\n", " <td>10.0</td>\n", " <td>NaN</td>\n", " <td>NaN</td>\n", " <td>NaN</td>\n", - " <td>NaN</td>\n", + " <td>1.0</td>\n", " <td>...</td>\n", " <td>NaN</td>\n", - " <td>47970</td>\n", - " <td>47970</td>\n", - " <td>47970</td>\n", + " <td>54190</td>\n", + " <td>54190</td>\n", + " <td>54190</td>\n", " <td>2</td>\n", " <td>0.0</td>\n", " <td>0.0</td>\n", - " <td>1594.0</td>\n", - " <td>13.0</td>\n", - " <td>1607.0</td>\n", + " <td>2462.0</td>\n", + " <td>33.0</td>\n", + " <td>2495.0</td>\n", " </tr>\n", " <tr>\n", " <th>1</th>\n", - " <td>20200528</td>\n", + " <td>20200601</td>\n", " <td>AL</td>\n", - " <td>16310.0</td>\n", - " <td>184171.0</td>\n", + " <td>18363.0</td>\n", + " <td>205160.0</td>\n", " <td>NaN</td>\n", " <td>NaN</td>\n", - " <td>1765.0</td>\n", + " <td>1856.0</td>\n", " <td>NaN</td>\n", - " <td>566.0</td>\n", + " <td>591.0</td>\n", " <td>NaN</td>\n", " <td>...</td>\n", - " <td>1765.0</td>\n", - " <td>200481</td>\n", - " <td>200481</td>\n", - " <td>200481</td>\n", + " <td>1856.0</td>\n", + " <td>223523</td>\n", + " <td>223523</td>\n", + " <td>223523</td>\n", " <td>1</td>\n", - " <td>9.0</td>\n", - " <td>46.0</td>\n", - " <td>4220.0</td>\n", - " <td>467.0</td>\n", - " <td>4687.0</td>\n", + " <td>15.0</td>\n", + " <td>12.0</td>\n", + " <td>5510.0</td>\n", + " <td>460.0</td>\n", + " <td>5970.0</td>\n", " </tr>\n", " </tbody>\n", "</table>\n", @@ -421,24 +421,24 @@ ], "text/plain": [ " date state positive negative pending hospitalizedCurrently \\\n", - "0 20200528 AK 425.0 47545.0 NaN 10.0 \n", - "1 20200528 AL 16310.0 184171.0 NaN NaN \n", + "0 20200601 AK 467.0 53723.0 NaN 10.0 \n", + "1 20200601 AL 18363.0 205160.0 NaN NaN \n", "\n", " hospitalizedCumulative inIcuCurrently inIcuCumulative \\\n", "0 NaN NaN NaN \n", - "1 1765.0 NaN 566.0 \n", + "1 1856.0 NaN 591.0 \n", "\n", " onVentilatorCurrently ... hospitalized total totalTestResults posNeg \\\n", - "0 NaN ... NaN 47970 47970 47970 \n", - "1 NaN ... 1765.0 200481 200481 200481 \n", + "0 1.0 ... NaN 54190 54190 54190 \n", + "1 NaN ... 1856.0 223523 223523 223523 \n", "\n", " fips deathIncrease hospitalizedIncrease negativeIncrease \\\n", - "0 2 0.0 0.0 1594.0 \n", - "1 1 9.0 46.0 4220.0 \n", + "0 2 0.0 0.0 2462.0 \n", + "1 1 15.0 12.0 5510.0 \n", "\n", " positiveIncrease totalTestResultsIncrease \n", - "0 13.0 1607.0 \n", - "1 467.0 4687.0 \n", + "0 33.0 2495.0 \n", + "1 460.0 5970.0 \n", "\n", "[2 rows x 27 columns]" ] @@ -474,18 +474,18 @@ "version": "3.7.3" }, "papermill": { - "duration": 11.277959, - "end_time": "2020-05-29T07:27:38.075952", + "duration": 8.164183, + "end_time": "2020-06-02T08:11:16.160309", "environment_variables": {}, "exception": null, - "input_path": "/tmp/8w_tcx45/notebooks/process/download-covidtracking-data.ipynb", + "input_path": "/tmp/_29it5g5/notebooks/process/download-covidtracking-data.ipynb", "output_path": "runs/download-covidtracking-data.runs.ipynb", "parameters": { - "PAPERMILL_INPUT_PATH": "/tmp/8w_tcx45/notebooks/process/download-covidtracking-data.ipynb", + "PAPERMILL_INPUT_PATH": "/tmp/_29it5g5/notebooks/process/download-covidtracking-data.ipynb", "PAPERMILL_OUTPUT_PATH": "runs/download-covidtracking-data.runs.ipynb", "out_folder": "data/covidtracking" }, - "start_time": "2020-05-29T07:27:26.797993", + "start_time": "2020-06-02T08:11:07.996126", "version": "1.1.0" } },