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

50366b9b · CI-bot · renku 0.10.4 · 3b60894f · 50366b9b · 50366b9b
Commit 50366b9b authored 4 years ago by CI-bot Committed by renku 0.10.4 4 years ago
--- a/.renku/workflow/af5dfb58f2b24a47982f53bc439eb361.cwl
+++ b/.renku/workflow/af5dfb58f2b24a47982f53bc439eb361.cwl
+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_2:
+    outputSource: step_2/output_1
+    streamable: false
+    type: Directory
+  output_3:
+    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-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_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-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: []
--- 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": 0.907046,
-     "end_time": "2020-07-30T14:24:08.534068",
+     "duration": 0.636339,
+     "end_time": "2020-07-31T07:31:38.916840",
     "exception": false,
-     "start_time": "2020-07-30T14:24:07.627022",
+     "start_time": "2020-07-31T07:31:38.280501",
     "status": "completed"
    },
    "tags": []
@@ -25,10 +25,10 @@
   "execution_count": 2,
   "metadata": {
    "papermill": {
-     "duration": 0.017285,
-     "end_time": "2020-07-30T14:24:08.564468",
+     "duration": 0.017811,
+     "end_time": "2020-07-31T07:31:38.947335",
     "exception": false,
-     "start_time": "2020-07-30T14:24:08.547183",
+     "start_time": "2020-07-31T07:31:38.929524",
     "status": "completed"
    },
    "tags": [
@@ -46,10 +46,10 @@
   "execution_count": 3,
   "metadata": {
    "papermill": {
-     "duration": 0.019325,
-     "end_time": "2020-07-30T14:24:08.591665",
+     "duration": 0.019772,
+     "end_time": "2020-07-31T07:31:38.974996",
     "exception": false,
-     "start_time": "2020-07-30T14:24:08.572340",
+     "start_time": "2020-07-31T07:31:38.955224",
     "status": "completed"
    },
    "tags": [
@@ -59,7 +59,7 @@
   "outputs": [],
   "source": [
    "# Parameters\n",
-    "PAPERMILL_INPUT_PATH = \"/tmp/fjybgsvd/notebooks/process/download-covidtracking-data.ipynb\"\n",
+    "PAPERMILL_INPUT_PATH = \"/tmp/z_m8yogb/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": 0.009349,
-     "end_time": "2020-07-30T14:24:08.610870",
+     "duration": 0.006274,
+     "end_time": "2020-07-31T07:31:38.988972",
     "exception": false,
-     "start_time": "2020-07-30T14:24:08.601521",
+     "start_time": "2020-07-31T07:31:38.982698",
     "status": "completed"
    },
    "tags": []
@@ -87,10 +87,10 @@
   "execution_count": 4,
   "metadata": {
    "papermill": {
-     "duration": 0.204592,
-     "end_time": "2020-07-30T14:24:08.822751",
+     "duration": 0.31111,
+     "end_time": "2020-07-31T07:31:39.306628",
     "exception": false,
-     "start_time": "2020-07-30T14:24:08.618159",
+     "start_time": "2020-07-31T07:31:38.995518",
     "status": "completed"
    },
    "tags": []
@@ -107,10 +107,10 @@
   "execution_count": 5,
   "metadata": {
    "papermill": {
-     "duration": 0.020289,
-     "end_time": "2020-07-30T14:24:08.853913",
+     "duration": 0.019968,
+     "end_time": "2020-07-31T07:31:39.336696",
     "exception": false,
-     "start_time": "2020-07-30T14:24:08.833624",
+     "start_time": "2020-07-31T07:31:39.316728",
     "status": "completed"
    },
    "tags": []
@@ -129,10 +129,10 @@
   "execution_count": 6,
   "metadata": {
    "papermill": {
-     "duration": 0.062187,
-     "end_time": "2020-07-30T14:24:08.924813",
+     "duration": 0.058807,
+     "end_time": "2020-07-31T07:31:39.403115",
     "exception": false,
-     "start_time": "2020-07-30T14:24:08.862626",
+     "start_time": "2020-07-31T07:31:39.344308",
     "status": "completed"
    },
    "tags": []
@@ -249,10 +249,10 @@
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
-     "duration": 0.0084,
-     "end_time": "2020-07-30T14:24:08.943709",
+     "duration": 0.007059,
+     "end_time": "2020-07-31T07:31:39.417766",
     "exception": false,
-     "start_time": "2020-07-30T14:24:08.935309",
+     "start_time": "2020-07-31T07:31:39.410707",
     "status": "completed"
    },
    "tags": []
@@ -266,10 +266,10 @@
   "execution_count": 7,
   "metadata": {
    "papermill": {
-     "duration": 0.227722,
-     "end_time": "2020-07-30T14:24:09.179458",
+     "duration": 0.234612,
+     "end_time": "2020-07-31T07:31:39.659826",
     "exception": false,
-     "start_time": "2020-07-30T14:24:08.951736",
+     "start_time": "2020-07-31T07:31:39.425214",
     "status": "completed"
    },
    "tags": []
@@ -286,10 +286,10 @@
   "execution_count": 8,
   "metadata": {
    "papermill": {
-     "duration": 0.027108,
-     "end_time": "2020-07-30T14:24:09.220333",
+     "duration": 0.029778,
+     "end_time": "2020-07-31T07:31:39.701277",
     "exception": false,
-     "start_time": "2020-07-30T14:24:09.193225",
+     "start_time": "2020-07-31T07:31:39.671499",
     "status": "completed"
    },
    "tags": []
@@ -308,10 +308,10 @@
   "execution_count": 9,
   "metadata": {
    "papermill": {
-     "duration": 0.309148,
-     "end_time": "2020-07-30T14:24:09.540890",
+     "duration": 0.346106,
+     "end_time": "2020-07-31T07:31:40.058722",
     "exception": false,
-     "start_time": "2020-07-30T14:24:09.231742",
+     "start_time": "2020-07-31T07:31:39.712616",
     "status": "completed"
    },
    "tags": []
@@ -321,7 +321,7 @@
     "name": "stdout",
     "output_type": "stream",
     "text": [
-      "8193 data points\n"
+      "8249 data points\n"
     ]
    },
    {
@@ -371,10 +371,10 @@
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
-       "      <td>20200729</td>\n",
+       "      <td>20200730</td>\n",
       "      <td>AK</td>\n",
-       "      <td>3442.0</td>\n",
-       "      <td>220222.0</td>\n",
+       "      <td>3559.0</td>\n",
+       "      <td>221498.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>45.0</td>\n",
       "      <td>NaN</td>\n",
@@ -382,10 +382,10 @@
       "      <td>NaN</td>\n",
       "      <td>3.0</td>\n",
       "      <td>...</td>\n",
-       "      <td>223664</td>\n",
-       "      <td>0</td>\n",
+       "      <td>225057</td>\n",
+       "      <td>1</td>\n",
       "      <td>0</td>\n",
-       "      <td>e3c05df1cf92b9c80941cec8daaf723905e7a0dd</td>\n",
+       "      <td>d66445af73028a02a5d6713580a4c470cc603322</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>20200729</td>\n",
+       "      <td>20200730</td>\n",
       "      <td>AL</td>\n",
-       "      <td>83782.0</td>\n",
-       "      <td>584493.0</td>\n",
+       "      <td>85762.0</td>\n",
+       "      <td>594346.0</td>\n",
       "      <td>NaN</td>\n",
-       "      <td>1598.0</td>\n",
-       "      <td>9893.0</td>\n",
+       "      <td>1595.0</td>\n",
+       "      <td>10070.0</td>\n",
       "      <td>NaN</td>\n",
-       "      <td>1109.0</td>\n",
+       "      <td>1129.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
-       "      <td>668275</td>\n",
-       "      <td>47</td>\n",
-       "      <td>0</td>\n",
-       "      <td>a7b049cfd14780e56e6ef98fb2aba9f82fe89838</td>\n",
+       "      <td>680108</td>\n",
+       "      <td>27</td>\n",
+       "      <td>177</td>\n",
+       "      <td>5776f9724a3452e48705a9b2c73f52d3e631229d</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  20200729    AK    3442.0  220222.0      NaN                   45.0   \n",
-       "1  20200729    AL   83782.0  584493.0      NaN                 1598.0   \n",
+       "0  20200730    AK    3559.0  221498.0      NaN                   45.0   \n",
+       "1  20200730    AL   85762.0  594346.0      NaN                 1595.0   \n",
       "\n",
       "   hospitalizedCumulative  inIcuCurrently  inIcuCumulative  \\\n",
       "0                     NaN             NaN              NaN   \n",
-       "1                  9893.0             NaN           1109.0   \n",
+       "1                 10070.0             NaN           1129.0   \n",
       "\n",
       "   onVentilatorCurrently  ...  posNeg  deathIncrease hospitalizedIncrease  \\\n",
-       "0                    3.0  ...  223664              0                    0   \n",
-       "1                    NaN  ...  668275             47                    0   \n",
+       "0                    3.0  ...  225057              1                    0   \n",
+       "1                    NaN  ...  680108             27                  177   \n",
       "\n",
       "                                       hash commercialScore  \\\n",
-       "0  e3c05df1cf92b9c80941cec8daaf723905e7a0dd               0   \n",
-       "1  a7b049cfd14780e56e6ef98fb2aba9f82fe89838               0   \n",
+       "0  d66445af73028a02a5d6713580a4c470cc603322               0   \n",
+       "1  5776f9724a3452e48705a9b2c73f52d3e631229d               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": 3.334052,
-   "end_time": "2020-07-30T14:24:09.864496",
+   "duration": 3.000062,
+   "end_time": "2020-07-31T07:31:40.379070",
   "environment_variables": {},
   "exception": null,
-   "input_path": "/tmp/fjybgsvd/notebooks/process/download-covidtracking-data.ipynb",
+   "input_path": "/tmp/z_m8yogb/notebooks/process/download-covidtracking-data.ipynb",
   "output_path": "runs/download-covidtracking-data.runs.ipynb",
   "parameters": {
-    "PAPERMILL_INPUT_PATH": "/tmp/fjybgsvd/notebooks/process/download-covidtracking-data.ipynb",
+    "PAPERMILL_INPUT_PATH": "/tmp/z_m8yogb/notebooks/process/download-covidtracking-data.ipynb",
    "PAPERMILL_OUTPUT_PATH": "runs/download-covidtracking-data.runs.ipynb",
    "out_folder": "data/covidtracking"
   },
-   "start_time": "2020-07-30T14:24:06.530444",
+   "start_time": "2020-07-31T07:31:37.379008",
   "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/fjybgsvd/notebooks/process/download-covidtracking-data.ipynb"
+PAPERMILL_INPUT_PATH = "/tmp/z_m8yogb/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  Negatives = (Totals – Positives)\nPositives oc...
    1    AL  Negatives = (Totals - Positives) \nPositives o...
    
                                             covid19Site  \
    0  http://dhss.alaska.gov/dph/Epi/id/Pages/COVID-...
    1  https://alpublichealth.maps.arcgis.com/apps/op...
    
                                    covid19SiteSecondary  \
    0  http://dhss.alaska.gov/dph/Epi/id/Pages/COVID-...
    1            https://dph1.adph.state.al.us/covid-19/
    
                                     covid19SiteTertiary          twitter  \
    0  https://alaska-dhss.maps.arcgis.com/apps/opsda...     @Alaska_DHSS
    1                                                     @alpublichealth
    
                                          covid19SiteOld     name  fips pui    pum
    0  http://dhss.alaska.gov/dph/Epi/id/Pages/COVID-...   Alaska     2      False
    1  http://www.alabamapublichealth.gov/infectiousd...  Alabama     1      False

 %% 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

-    8193 data points
+    8249 data points

           date state  positive  negative  pending  hospitalizedCurrently  \
-    0  20200729    AK    3442.0  220222.0      NaN                   45.0
-    1  20200729    AL   83782.0  584493.0      NaN                 1598.0
+    0  20200730    AK    3559.0  221498.0      NaN                   45.0
+    1  20200730    AL   85762.0  594346.0      NaN                 1595.0
    
       hospitalizedCumulative  inIcuCurrently  inIcuCumulative  \
    0                     NaN             NaN              NaN
-    1                  9893.0             NaN           1109.0
+    1                 10070.0             NaN           1129.0
    
       onVentilatorCurrently  ...  posNeg  deathIncrease hospitalizedIncrease  \
-    0                    3.0  ...  223664              0                    0
-    1                    NaN  ...  668275             47                    0
+    0                    3.0  ...  225057              1                    0
+    1                    NaN  ...  680108             27                  177
    
                                           hash commercialScore  \
-    0  e3c05df1cf92b9c80941cec8daaf723905e7a0dd               0
-    1  a7b049cfd14780e56e6ef98fb2aba9f82fe89838               0
+    0  d66445af73028a02a5d6713580a4c470cc603322               0
+    1  5776f9724a3452e48705a9b2c73f52d3e631229d               0
    
      negativeRegularScore  negativeScore  positiveScore score  grade
    0                    0              0              0     0
    1                    0              0              0     0
    
    [2 rows x 41 columns]