renku rerun data/covidtracking/states-metadata.json data/covidtracking/states-daily.json

46e3de83 · CI-bot · renku 0.10.4 · 2a900767 · 46e3de83 · 46e3de83
Commit 46e3de83 authored 4 years ago by CI-bot Committed by renku 0.10.4 4 years ago
--- a/.renku/workflow/fee2db68809c45de96163347d55b9425.cwl
+++ b/.renku/workflow/fee2db68809c45de96163347d55b9425.cwl
+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_2:
+    outputSource: step_2/output_0
+    streamable: false
+    type: File
+  output_3:
+    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-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: []
--- a/data/covidtracking/states-daily.json
+++ b/data/covidtracking/states-daily.json
--- a/data/covidtracking/states-metadata.json
+++ b/data/covidtracking/states-metadata.json
--- a/runs/download-covidtracking-data.runs.ipynb
+++ b/runs/download-covidtracking-data.runs.ipynb
@@ -5,10 +5,10 @@
   "execution_count": 1,
   "metadata": {
    "papermill": {
-     "duration": 4.788875,
-     "end_time": "2020-12-03T07:38:28.465846",
+     "duration": 4.531192,
+     "end_time": "2020-12-04T07:37:06.722979",
     "exception": false,
-     "start_time": "2020-12-03T07:38:23.676971",
+     "start_time": "2020-12-04T07:37:02.191787",
     "status": "completed"
    },
    "tags": []
@@ -25,10 +25,10 @@
   "execution_count": 2,
   "metadata": {
    "papermill": {
-     "duration": 0.019484,
-     "end_time": "2020-12-03T07:38:28.499005",
+     "duration": 0.020784,
+     "end_time": "2020-12-04T07:37:06.757030",
     "exception": false,
-     "start_time": "2020-12-03T07:38:28.479521",
+     "start_time": "2020-12-04T07:37:06.736246",
     "status": "completed"
    },
    "tags": [
@@ -46,10 +46,10 @@
   "execution_count": 3,
   "metadata": {
    "papermill": {
-     "duration": 0.011148,
-     "end_time": "2020-12-03T07:38:28.517058",
+     "duration": 0.021,
+     "end_time": "2020-12-04T07:37:06.785589",
     "exception": false,
-     "start_time": "2020-12-03T07:38:28.505910",
+     "start_time": "2020-12-04T07:37:06.764589",
     "status": "completed"
    },
    "tags": [
@@ -59,7 +59,7 @@
   "outputs": [],
   "source": [
    "# Parameters\n",
-    "PAPERMILL_INPUT_PATH = \"/tmp/18hdod4w/notebooks/process/download-covidtracking-data.ipynb\"\n",
+    "PAPERMILL_INPUT_PATH = \"/tmp/4jh789g5/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": 0.004225,
-     "end_time": "2020-12-03T07:38:28.525806",
+     "duration": 0.007858,
+     "end_time": "2020-12-04T07:37:06.804981",
     "exception": false,
-     "start_time": "2020-12-03T07:38:28.521581",
+     "start_time": "2020-12-04T07:37:06.797123",
     "status": "completed"
    },
    "tags": []
@@ -87,10 +87,10 @@
   "execution_count": 4,
   "metadata": {
    "papermill": {
-     "duration": 0.355297,
-     "end_time": "2020-12-03T07:38:28.885395",
+     "duration": 0.443813,
+     "end_time": "2020-12-04T07:37:07.254800",
     "exception": false,
-     "start_time": "2020-12-03T07:38:28.530098",
+     "start_time": "2020-12-04T07:37:06.810987",
     "status": "completed"
    },
    "tags": []
@@ -107,10 +107,10 @@
   "execution_count": 5,
   "metadata": {
    "papermill": {
-     "duration": 0.014069,
-     "end_time": "2020-12-03T07:38:28.908662",
+     "duration": 0.023261,
+     "end_time": "2020-12-04T07:37:07.291923",
     "exception": false,
-     "start_time": "2020-12-03T07:38:28.894593",
+     "start_time": "2020-12-04T07:37:07.268662",
     "status": "completed"
    },
    "tags": []
@@ -129,10 +129,10 @@
   "execution_count": 6,
   "metadata": {
    "papermill": {
-     "duration": 0.057278,
-     "end_time": "2020-12-03T07:38:28.970747",
+     "duration": 0.06675,
+     "end_time": "2020-12-04T07:37:07.366359",
     "exception": false,
-     "start_time": "2020-12-03T07:38:28.913469",
+     "start_time": "2020-12-04T07:37:07.299609",
     "status": "completed"
    },
    "tags": []
@@ -284,10 +284,10 @@
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
-     "duration": 0.004708,
-     "end_time": "2020-12-03T07:38:28.981128",
+     "duration": 0.007091,
+     "end_time": "2020-12-04T07:37:07.384941",
     "exception": false,
-     "start_time": "2020-12-03T07:38:28.976420",
+     "start_time": "2020-12-04T07:37:07.377850",
     "status": "completed"
    },
    "tags": []
@@ -301,10 +301,10 @@
   "execution_count": 7,
   "metadata": {
    "papermill": {
-     "duration": 0.611817,
-     "end_time": "2020-12-03T07:38:29.597559",
+     "duration": 0.642862,
+     "end_time": "2020-12-04T07:37:08.033860",
     "exception": false,
-     "start_time": "2020-12-03T07:38:28.985742",
+     "start_time": "2020-12-04T07:37:07.390998",
     "status": "completed"
    },
    "tags": []
@@ -321,10 +321,10 @@
   "execution_count": 8,
   "metadata": {
    "papermill": {
-     "duration": 0.050611,
-     "end_time": "2020-12-03T07:38:29.662663",
+     "duration": 0.058701,
+     "end_time": "2020-12-04T07:37:08.109308",
     "exception": false,
-     "start_time": "2020-12-03T07:38:29.612052",
+     "start_time": "2020-12-04T07:37:08.050607",
     "status": "completed"
    },
    "tags": []
@@ -343,10 +343,10 @@
   "execution_count": 9,
   "metadata": {
    "papermill": {
-     "duration": 0.583797,
-     "end_time": "2020-12-03T07:38:30.259718",
+     "duration": 0.506741,
+     "end_time": "2020-12-04T07:37:08.629737",
     "exception": false,
-     "start_time": "2020-12-03T07:38:29.675921",
+     "start_time": "2020-12-04T07:37:08.122996",
     "status": "completed"
    },
    "tags": []
@@ -356,7 +356,7 @@
     "name": "stdout",
     "output_type": "stream",
     "text": [
-      "15409 data points\n"
+      "15465 data points\n"
     ]
    },
    {
@@ -406,21 +406,21 @@
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
-       "      <td>20201202</td>\n",
+       "      <td>20201203</td>\n",
       "      <td>AK</td>\n",
-       "      <td>32531.0</td>\n",
+       "      <td>33291.0</td>\n",
       "      <td>NaN</td>\n",
-       "      <td>992112.0</td>\n",
+       "      <td>1007214.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>totalTestsViral</td>\n",
-       "      <td>1024643.0</td>\n",
-       "      <td>164.0</td>\n",
-       "      <td>768.0</td>\n",
+       "      <td>1040505.0</td>\n",
+       "      <td>157.0</td>\n",
+       "      <td>783.0</td>\n",
       "      <td>...</td>\n",
-       "      <td>1024643</td>\n",
-       "      <td>0</td>\n",
-       "      <td>19</td>\n",
-       "      <td>a67835c9975e7a741cbe7511d7b8014f238f7381</td>\n",
+       "      <td>1040505</td>\n",
+       "      <td>8</td>\n",
+       "      <td>15</td>\n",
+       "      <td>2681286b4959bcec2a503789d53119c645f4b0c6</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
@@ -430,21 +430,21 @@
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
-       "      <td>20201202</td>\n",
+       "      <td>20201203</td>\n",
       "      <td>AL</td>\n",
-       "      <td>256828.0</td>\n",
-       "      <td>43656.0</td>\n",
-       "      <td>1390351.0</td>\n",
+       "      <td>260359.0</td>\n",
+       "      <td>44421.0</td>\n",
+       "      <td>1400010.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>totalTestsPeopleViral</td>\n",
-       "      <td>1603523.0</td>\n",
-       "      <td>1801.0</td>\n",
-       "      <td>25821.0</td>\n",
+       "      <td>1615948.0</td>\n",
+       "      <td>1827.0</td>\n",
+       "      <td>26062.0</td>\n",
       "      <td>...</td>\n",
-       "      <td>1647179</td>\n",
-       "      <td>73</td>\n",
-       "      <td>211</td>\n",
-       "      <td>4aa82c6006d2babec8c2e4268bc0d73e2681fe76</td>\n",
+       "      <td>1660369</td>\n",
+       "      <td>65</td>\n",
+       "      <td>241</td>\n",
+       "      <td>d333019ec43ddf9c5c4ec262bc5ed78ee214f19b</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
@@ -459,20 +459,20 @@
      ],
      "text/plain": [
       "       date state  positive  probableCases   negative  pending  \\\n",
-       "0  20201202    AK   32531.0            NaN   992112.0      NaN   \n",
-       "1  20201202    AL  256828.0        43656.0  1390351.0      NaN   \n",
+       "0  20201203    AK   33291.0            NaN  1007214.0      NaN   \n",
+       "1  20201203    AL  260359.0        44421.0  1400010.0      NaN   \n",
       "\n",
       "  totalTestResultsSource  totalTestResults  hospitalizedCurrently  \\\n",
-       "0        totalTestsViral         1024643.0                  164.0   \n",
-       "1  totalTestsPeopleViral         1603523.0                 1801.0   \n",
+       "0        totalTestsViral         1040505.0                  157.0   \n",
+       "1  totalTestsPeopleViral         1615948.0                 1827.0   \n",
       "\n",
       "   hospitalizedCumulative  ...   posNeg  deathIncrease  hospitalizedIncrease  \\\n",
-       "0                   768.0  ...  1024643              0                    19   \n",
-       "1                 25821.0  ...  1647179             73                   211   \n",
+       "0                   783.0  ...  1040505              8                    15   \n",
+       "1                 26062.0  ...  1660369             65                   241   \n",
       "\n",
       "                                       hash  commercialScore  \\\n",
-       "0  a67835c9975e7a741cbe7511d7b8014f238f7381                0   \n",
-       "1  4aa82c6006d2babec8c2e4268bc0d73e2681fe76                0   \n",
+       "0  2681286b4959bcec2a503789d53119c645f4b0c6                0   \n",
+       "1  d333019ec43ddf9c5c4ec262bc5ed78ee214f19b                0   \n",
       "\n",
       "  negativeRegularScore negativeScore positiveScore score  grade  \n",
       "0                    0             0             0     0         \n",
@@ -512,18 +512,18 @@
   "version": "3.7.3"
  },
  "papermill": {
-   "duration": 8.673797,
-   "end_time": "2020-12-03T07:38:30.582322",
+   "duration": 8.083653,
+   "end_time": "2020-12-04T07:37:08.951693",
   "environment_variables": {},
   "exception": null,
-   "input_path": "/tmp/18hdod4w/notebooks/process/download-covidtracking-data.ipynb",
+   "input_path": "/tmp/4jh789g5/notebooks/process/download-covidtracking-data.ipynb",
   "output_path": "runs/download-covidtracking-data.runs.ipynb",
   "parameters": {
-    "PAPERMILL_INPUT_PATH": "/tmp/18hdod4w/notebooks/process/download-covidtracking-data.ipynb",
+    "PAPERMILL_INPUT_PATH": "/tmp/4jh789g5/notebooks/process/download-covidtracking-data.ipynb",
    "PAPERMILL_OUTPUT_PATH": "runs/download-covidtracking-data.runs.ipynb",
    "out_folder": "data/covidtracking"
   },
-   "start_time": "2020-12-03T07:38:21.908525",
+   "start_time": "2020-12-04T07:37:00.868040",
   "version": "1.1.0"
  }
 },

 %% Cell type:code id: tags:

 ``` python
 import requests
 import os
 import pandas as pd
 ```

 %% Cell type:code id: tags:parameters

 ``` python
 out_folder = "../data/covidtracking/"
 PAPERMILL_OUTPUT_PATH = None
 ```

 %% Cell type:code id: tags:injected-parameters

 ``` python
 # Parameters
-PAPERMILL_INPUT_PATH = "/tmp/18hdod4w/notebooks/process/download-covidtracking-data.ipynb"
+PAPERMILL_INPUT_PATH = "/tmp/4jh789g5/notebooks/process/download-covidtracking-data.ipynb"
 PAPERMILL_OUTPUT_PATH = "runs/download-covidtracking-data.runs.ipynb"
 out_folder = "data/covidtracking"
 ```

 %% Cell type:markdown id: tags:

 # Download state metadata

 Download a dataset of URLs for data for each US state and several territories. See [Google Doc](https://docs.google.com/spreadsheets/d/18oVRrHj3c183mHmq3m89_163yuYltLNlOmPerQ18E8w/htmlview?sle=true).

 %% Cell type:code id: tags:

 ``` python
 url = 'http://covidtracking.com/api/states/info'
 r = requests.get(url, allow_redirects=True)
 states_metadata_json = r.content
 ```

 %% Cell type:code id: tags:

 ``` python
 # save the result
 if PAPERMILL_OUTPUT_PATH:
    out_path = os.path.join(out_folder, 'states-metadata.json')
    with open(out_path, 'wb') as f:
        f.write(states_metadata_json)
 ```

 %% Cell type:code id: tags:

 ``` python
 metadata_df = pd.read_json(states_metadata_json)
 print(len(metadata_df), "states and territories have metadata")
 metadata_df.head(2)
 ```

 %% Output

    56 states and territories have metadata

      state                                              notes  \
    0    AK  Alaska combines PCR and antigen tests in the t...
    1    AL  Alabama combines PCR and antigen tests in the ...
    
                                             covid19Site  \
    0  http://dhss.alaska.gov/dph/Epi/id/Pages/COVID-...
    1  https://alpublichealth.maps.arcgis.com/apps/op...
    
                                    covid19SiteSecondary  \
    0  https://experience.arcgis.com/experience/ed1c8...
    1  https://alpublichealth.maps.arcgis.com/apps/op...
    
                                     covid19SiteTertiary  \
    0  https://alaska-dhss.maps.arcgis.com/apps/opsda...
    1  https://services7.arcgis.com/4RQmZZ0yaZkGR1zy/...
    
                                   covid19SiteQuaternary  \
    0  https://services1.arcgis.com/WzFsmainVTuD5KML/...
    1                                               None
    
                                      covid19SiteQuinary          twitter  \
    0  https://services1.arcgis.com/WzFsmainVTuD5KML/...     @Alaska_DHSS
    1                                               None  @alpublichealth
    
                                          covid19SiteOld  \
    0  http://dhss.alaska.gov/dph/Epi/id/Pages/COVID-...
    1  http://www.alabamapublichealth.gov/infectiousd...
    
      covidTrackingProjectPreferredTotalTestUnits  \
    0                                   Specimens
    1                                      People
    
      covidTrackingProjectPreferredTotalTestField     totalTestResultsField  \
    0                             totalTestsViral         Total Tests (PCR)
    1                       totalTestsPeopleViral  Total PCR Tests (People)
    
            pui    pum     name  fips
    0  All data  False   Alaska     2
    1   No data  False  Alabama     1

 %% Cell type:markdown id: tags:

 # Download daily state data

 %% Cell type:code id: tags:

 ``` python
 url = 'https://covidtracking.com/api/states/daily'
 r = requests.get(url, allow_redirects=True)
 states_daily_json = r.content
 ```

 %% Cell type:code id: tags:

 ``` python
 # save the result
 if PAPERMILL_OUTPUT_PATH:
    out_path = os.path.join(out_folder, 'states-daily.json')
    with open(out_path, 'wb') as f:
        f.write(states_daily_json)
 ```

 %% Cell type:code id: tags:

 ``` python
 data_df = pd.read_json(states_daily_json)
 print(len(data_df), "data points")
 data_df.head(2)
 ```

 %% Output

-    15409 data points
+    15465 data points

           date state  positive  probableCases   negative  pending  \
-    0  20201202    AK   32531.0            NaN   992112.0      NaN
-    1  20201202    AL  256828.0        43656.0  1390351.0      NaN
+    0  20201203    AK   33291.0            NaN  1007214.0      NaN
+    1  20201203    AL  260359.0        44421.0  1400010.0      NaN
    
      totalTestResultsSource  totalTestResults  hospitalizedCurrently  \
-    0        totalTestsViral         1024643.0                  164.0
-    1  totalTestsPeopleViral         1603523.0                 1801.0
+    0        totalTestsViral         1040505.0                  157.0
+    1  totalTestsPeopleViral         1615948.0                 1827.0
    
       hospitalizedCumulative  ...   posNeg  deathIncrease  hospitalizedIncrease  \
-    0                   768.0  ...  1024643              0                    19
-    1                 25821.0  ...  1647179             73                   211
+    0                   783.0  ...  1040505              8                    15
+    1                 26062.0  ...  1660369             65                   241
    
                                           hash  commercialScore  \
-    0  a67835c9975e7a741cbe7511d7b8014f238f7381                0
-    1  4aa82c6006d2babec8c2e4268bc0d73e2681fe76                0
+    0  2681286b4959bcec2a503789d53119c645f4b0c6                0
+    1  d333019ec43ddf9c5c4ec262bc5ed78ee214f19b                0
    
      negativeRegularScore negativeScore positiveScore score  grade
    0                    0             0             0     0
    1                    0             0             0     0
    
    [2 rows x 55 columns]