From ccc37edffe6d9ca8ea4b8a229d1d20c42bc4b658 Mon Sep 17 00:00:00 2001
From: Chandrasekhar Ramakrishnan <cramakri@ethz.ch>
Date: Thu, 26 Mar 2020 12:38:34 +0000
Subject: [PATCH] renku run papermill -p out_folder ./data/covidtracking/
--inject-paths notebooks/process/download-covidtracking-data.ipynb
runs/download-covidtracking-data.runs.ipynb
---
...560c41a54f5aa307ce5f3c5effe5_papermill.cwl | 70 ++++++++
data/covidtracking/states-daily.json | 4 +-
data/covidtracking/states-metadata.json | 4 +-
runs/download-covidtracking-data.runs.ipynb | 157 +++++++++++-------
4 files changed, 169 insertions(+), 66 deletions(-)
create mode 100644 .renku/workflow/a17d560c41a54f5aa307ce5f3c5effe5_papermill.cwl
diff --git a/.renku/workflow/a17d560c41a54f5aa307ce5f3c5effe5_papermill.cwl b/.renku/workflow/a17d560c41a54f5aa307ce5f3c5effe5_papermill.cwl
new file mode 100644
index 00000000..8ab0a3b5
--- /dev/null
+++ b/.renku/workflow/a17d560c41a54f5aa307ce5f3c5effe5_papermill.cwl
@@ -0,0 +1,70 @@
+arguments: []
+baseCommand:
+- papermill
+class: CommandLineTool
+cwlVersion: v1.0
+hints: []
+inputs:
+ input_1:
+ default: out_folder
+ inputBinding:
+ position: 1
+ prefix: -p
+ separate: true
+ shellQuote: true
+ streamable: false
+ type: string
+ input_2:
+ default: data/covidtracking
+ inputBinding:
+ position: 2
+ separate: true
+ shellQuote: true
+ streamable: false
+ type: string
+ input_3:
+ default:
+ class: File
+ path: ../../notebooks/process/download-covidtracking-data.ipynb
+ inputBinding:
+ position: 3
+ prefix: --inject-paths
+ separate: true
+ shellQuote: true
+ streamable: false
+ type: File
+ input_4:
+ default: runs/download-covidtracking-data.runs.ipynb
+ inputBinding:
+ position: 4
+ separate: true
+ shellQuote: true
+ streamable: false
+ type: string
+outputs:
+ output_0:
+ outputBinding:
+ glob: $(inputs.input_4)
+ streamable: false
+ type: File
+ output_1:
+ outputBinding:
+ glob: $(inputs.input_2)
+ streamable: false
+ type: Directory
+permanentFailCodes: []
+requirements:
+- class: InlineJavascriptRequirement
+- class: InitialWorkDirRequirement
+ listing:
+ - entry: '$({"listing": [], "class": "Directory"})'
+ entryname: runs
+ writable: true
+ - entry: '$({"listing": [], "class": "Directory"})'
+ entryname: data/covidtracking
+ writable: true
+ - entry: $(inputs.input_3)
+ entryname: notebooks/process/download-covidtracking-data.ipynb
+ writable: false
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/covidtracking/states-daily.json b/data/covidtracking/states-daily.json
index ee2b6bc8..de5cd65d 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 sha256:4b0927c74f3dbb27dacfddb47b00d2c543f8ec932625dc1502b3d048fcc2668e
-size 160445
+oid sha256:a6103d449cc2fd40e6dcdb9b4778817576adfde055d94c1152a5e73bda6a3e98
+size 322323
diff --git a/data/covidtracking/states-metadata.json b/data/covidtracking/states-metadata.json
index 08dcd867..a7a99acd 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 sha256:02330f655200284fbdaef1b3d4272cc84385c648ce7c3b73d910a0cacc3fa529
-size 25509
+oid sha256:12f495f7b6df119f781bdada37c7e80646b43458ae3b595ccbb83878980a6640
+size 27032
diff --git a/runs/download-covidtracking-data.runs.ipynb b/runs/download-covidtracking-data.runs.ipynb
index 5c6e420d..c1ef0273 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": 0.564716,
- "end_time": "2020-03-25T08:22:56.714459",
+ "duration": 0.506363,
+ "end_time": "2020-03-26T12:38:33.422061",
"exception": false,
- "start_time": "2020-03-25T08:22:56.149743",
+ "start_time": "2020-03-26T12:38:32.915698",
"status": "completed"
},
"tags": []
@@ -25,10 +25,10 @@
"execution_count": 2,
"metadata": {
"papermill": {
- "duration": 0.019507,
- "end_time": "2020-03-25T08:22:56.745116",
+ "duration": 0.020958,
+ "end_time": "2020-03-26T12:38:33.458041",
"exception": false,
- "start_time": "2020-03-25T08:22:56.725609",
+ "start_time": "2020-03-26T12:38:33.437083",
"status": "completed"
},
"tags": [
@@ -46,10 +46,10 @@
"execution_count": 3,
"metadata": {
"papermill": {
- "duration": 0.018572,
- "end_time": "2020-03-25T08:22:56.773076",
+ "duration": 0.023542,
+ "end_time": "2020-03-26T12:38:33.490779",
"exception": false,
- "start_time": "2020-03-25T08:22:56.754504",
+ "start_time": "2020-03-26T12:38:33.467237",
"status": "completed"
},
"tags": [
@@ -59,19 +59,19 @@
"outputs": [],
"source": [
"# Parameters\n",
- "PAPERMILL_INPUT_PATH = \"/tmp/e18fw9c9/notebooks/process/download-covidtracking-data.ipynb\"\n",
+ "PAPERMILL_INPUT_PATH = \"notebooks/process/download-covidtracking-data.ipynb\"\n",
"PAPERMILL_OUTPUT_PATH = \"runs/download-covidtracking-data.runs.ipynb\"\n",
- "out_folder = \"data/covidtracking\"\n"
+ "out_folder = \"./data/covidtracking/\"\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"papermill": {
- "duration": 0.007795,
- "end_time": "2020-03-25T08:22:56.790849",
+ "duration": 0.007637,
+ "end_time": "2020-03-26T12:38:33.508933",
"exception": false,
- "start_time": "2020-03-25T08:22:56.783054",
+ "start_time": "2020-03-26T12:38:33.501296",
"status": "completed"
},
"tags": []
@@ -87,10 +87,10 @@
"execution_count": 4,
"metadata": {
"papermill": {
- "duration": 1.020789,
- "end_time": "2020-03-25T08:22:57.818863",
+ "duration": 0.211295,
+ "end_time": "2020-03-26T12:38:33.726495",
"exception": false,
- "start_time": "2020-03-25T08:22:56.798074",
+ "start_time": "2020-03-26T12:38:33.515200",
"status": "completed"
},
"tags": []
@@ -107,10 +107,10 @@
"execution_count": 5,
"metadata": {
"papermill": {
- "duration": 0.022913,
- "end_time": "2020-03-25T08:22:57.852810",
+ "duration": 0.025576,
+ "end_time": "2020-03-26T12:38:33.768948",
"exception": false,
- "start_time": "2020-03-25T08:22:57.829897",
+ "start_time": "2020-03-26T12:38:33.743372",
"status": "completed"
},
"tags": []
@@ -129,10 +129,10 @@
"execution_count": 6,
"metadata": {
"papermill": {
- "duration": 0.066514,
- "end_time": "2020-03-25T08:22:57.927763",
+ "duration": 0.073344,
+ "end_time": "2020-03-26T12:38:33.849972",
"exception": false,
- "start_time": "2020-03-25T08:22:57.861249",
+ "start_time": "2020-03-26T12:38:33.776628",
"status": "completed"
},
"tags": []
@@ -174,6 +174,7 @@
" <th>pui</th>\n",
" <th>pum</th>\n",
" <th>notes</th>\n",
+ " <th>fips</th>\n",
" <th>name</th>\n",
" </tr>\n",
" </thead>\n",
@@ -188,6 +189,7 @@
" <td>All data</td>\n",
" <td>False</td>\n",
" <td>We count the reported number as \"persons teste...</td>\n",
+ " <td>2</td>\n",
" <td>Alaska</td>\n",
" </tr>\n",
" <tr>\n",
@@ -200,6 +202,7 @@
" <td>No data</td>\n",
" <td>False</td>\n",
" <td>Last update time taken from [main page](http:/...</td>\n",
+ " <td>1</td>\n",
" <td>Alabama</td>\n",
" </tr>\n",
" </tbody>\n",
@@ -219,9 +222,13 @@
"0 http://dhss.alaska.gov/dph/Epi/id/Pages/COVID-... @Alaska_DHSS \n",
"1 None @alpublichealth \n",
"\n",
- " pui pum notes name \n",
- "0 All data False We count the reported number as \"persons teste... Alaska \n",
- "1 No data False Last update time taken from [main page](http:/... Alabama "
+ " pui pum notes fips \\\n",
+ "0 All data False We count the reported number as \"persons teste... 2 \n",
+ "1 No data False Last update time taken from [main page](http:/... 1 \n",
+ "\n",
+ " name \n",
+ "0 Alaska \n",
+ "1 Alabama "
]
},
"execution_count": 6,
@@ -239,10 +246,10 @@
"cell_type": "markdown",
"metadata": {
"papermill": {
- "duration": 0.008089,
- "end_time": "2020-03-25T08:22:57.947587",
+ "duration": 0.007572,
+ "end_time": "2020-03-26T12:38:33.873621",
"exception": false,
- "start_time": "2020-03-25T08:22:57.939498",
+ "start_time": "2020-03-26T12:38:33.866049",
"status": "completed"
},
"tags": []
@@ -256,10 +263,10 @@
"execution_count": 7,
"metadata": {
"papermill": {
- "duration": 0.184993,
- "end_time": "2020-03-25T08:22:58.140940",
+ "duration": 0.178588,
+ "end_time": "2020-03-26T12:38:34.058549",
"exception": false,
- "start_time": "2020-03-25T08:22:57.955947",
+ "start_time": "2020-03-26T12:38:33.879961",
"status": "completed"
},
"tags": []
@@ -276,10 +283,10 @@
"execution_count": 8,
"metadata": {
"papermill": {
- "duration": 0.022977,
- "end_time": "2020-03-25T08:22:58.177014",
+ "duration": 0.027495,
+ "end_time": "2020-03-26T12:38:34.102339",
"exception": false,
- "start_time": "2020-03-25T08:22:58.154037",
+ "start_time": "2020-03-26T12:38:34.074844",
"status": "completed"
},
"tags": []
@@ -298,10 +305,10 @@
"execution_count": 9,
"metadata": {
"papermill": {
- "duration": 0.060602,
- "end_time": "2020-03-25T08:22:58.251228",
+ "duration": 0.076898,
+ "end_time": "2020-03-26T12:38:34.188602",
"exception": false,
- "start_time": "2020-03-25T08:22:58.190626",
+ "start_time": "2020-03-26T12:38:34.111704",
"status": "completed"
},
"tags": []
@@ -311,7 +318,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
- "1037 data points\n"
+ "1093 data points\n"
]
},
{
@@ -344,32 +351,50 @@
" <th>death</th>\n",
" <th>total</th>\n",
" <th>dateChecked</th>\n",
+ " <th>totalTestResults</th>\n",
+ " <th>deathIncrease</th>\n",
+ " <th>hospitalizedIncrease</th>\n",
+ " <th>negativeIncrease</th>\n",
+ " <th>positiveIncrease</th>\n",
+ " <th>totalTestResultsIncrease</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
- " <td>20200324</td>\n",
+ " <td>20200325</td>\n",
" <td>AK</td>\n",
- " <td>36.0</td>\n",
- " <td>986.0</td>\n",
- " <td>NaN</td>\n",
- " <td>0.0</td>\n",
+ " <td>42.0</td>\n",
+ " <td>1649.0</td>\n",
" <td>NaN</td>\n",
- " <td>1022</td>\n",
- " <td>2020-03-24T20:00:00Z</td>\n",
+ " <td>1.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>1691</td>\n",
+ " <td>2020-03-25T20:00:00Z</td>\n",
+ " <td>1691</td>\n",
+ " <td>1.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>663.0</td>\n",
+ " <td>6.0</td>\n",
+ " <td>669.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
- " <td>20200324</td>\n",
+ " <td>20200325</td>\n",
" <td>AL</td>\n",
- " <td>215.0</td>\n",
- " <td>2106.0</td>\n",
+ " <td>283.0</td>\n",
+ " <td>2529.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
- " <td>2321</td>\n",
- " <td>2020-03-24T20:00:00Z</td>\n",
+ " <td>2812</td>\n",
+ " <td>2020-03-25T20:00:00Z</td>\n",
+ " <td>2812</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>423.0</td>\n",
+ " <td>68.0</td>\n",
+ " <td>491.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
@@ -377,12 +402,20 @@
],
"text/plain": [
" date state positive negative pending hospitalized death total \\\n",
- "0 20200324 AK 36.0 986.0 NaN 0.0 NaN 1022 \n",
- "1 20200324 AL 215.0 2106.0 NaN NaN 0.0 2321 \n",
+ "0 20200325 AK 42.0 1649.0 NaN 1.0 1.0 1691 \n",
+ "1 20200325 AL 283.0 2529.0 NaN NaN 0.0 2812 \n",
+ "\n",
+ " dateChecked totalTestResults deathIncrease \\\n",
+ "0 2020-03-25T20:00:00Z 1691 1.0 \n",
+ "1 2020-03-25T20:00:00Z 2812 0.0 \n",
+ "\n",
+ " hospitalizedIncrease negativeIncrease positiveIncrease \\\n",
+ "0 1.0 663.0 6.0 \n",
+ "1 0.0 423.0 68.0 \n",
"\n",
- " dateChecked \n",
- "0 2020-03-24T20:00:00Z \n",
- "1 2020-03-24T20:00:00Z "
+ " totalTestResultsIncrease \n",
+ "0 669.0 \n",
+ "1 491.0 "
]
},
"execution_count": 9,
@@ -416,18 +449,18 @@
"version": "3.7.3"
},
"papermill": {
- "duration": 3.460914,
- "end_time": "2020-03-25T08:22:58.575452",
+ "duration": 2.475212,
+ "end_time": "2020-03-26T12:38:34.517904",
"environment_variables": {},
"exception": null,
- "input_path": "/tmp/e18fw9c9/notebooks/process/download-covidtracking-data.ipynb",
+ "input_path": "notebooks/process/download-covidtracking-data.ipynb",
"output_path": "runs/download-covidtracking-data.runs.ipynb",
"parameters": {
- "PAPERMILL_INPUT_PATH": "/tmp/e18fw9c9/notebooks/process/download-covidtracking-data.ipynb",
+ "PAPERMILL_INPUT_PATH": "notebooks/process/download-covidtracking-data.ipynb",
"PAPERMILL_OUTPUT_PATH": "runs/download-covidtracking-data.runs.ipynb",
- "out_folder": "data/covidtracking"
+ "out_folder": "./data/covidtracking/"
},
- "start_time": "2020-03-25T08:22:55.114538",
+ "start_time": "2020-03-26T12:38:32.042692",
"version": "1.1.0"
}
},
--
GitLab