wk2

DanielJanowicz · Aug 31, 2022 · 28d968c · 28d968c
1 parent ad1b1ec
commit 28d968c
Show file tree

Hide file tree

Showing 14 changed files with 191,143 additions and 3 deletions.
diff --git a/.gitignore b/.gitignore
@@ -8,3 +8,5 @@
 # ignore all .json files inside of ingestion/bigquery/
 ingestion/example_files/bigquery/**/*.json
 ingestion/example_files/bigquery/*.json
+
+
diff --git a/ingestion/example_files/json/Encounter-example-home.json b/ingestion/example_files/json/Encounter-example-home.json
@@ -27,6 +27,26 @@
       "reference": "Patient/example"
     },
     "participant": [
+      {
+        "period": {
+          "start": "2015-01-17T16:00:00+10:00",
+          "end": "2015-01-17T16:30:00+10:00"
+        },
+        "actor": {
+          "reference": "Practitioner/example",
+          "display": "Dr Adam Careful"
+        }
+      },
+      {
+        "period": {
+          "start": "2015-01-17T16:00:00+10:00",
+          "end": "2015-01-17T16:30:00+10:00"
+        },
+        "actor": {
+          "reference": "Practitioner/example",
+          "display": "Dr Adam Careful"
+        }
+      },
       {
         "period": {
           "start": "2015-01-17T16:00:00+10:00",

diff --git a/ingestion/example_files/xls_xlsx/AHQDataFile2016.xls b/ingestion/example_files/xls_xlsx/AHQDataFile2016.xls
diff --git a/ingestion/ingestion.py b/ingestion/ingestion.py
@@ -66,7 +66,7 @@
 # printing number of pages in pdf file
 print(pdfReader.numPages)
 # creating a page object
-pageObj = pdfReader.getPage(0)
+pageObj = pdfReader.getPage(1)
 # extracting text from page
 print(pageObj.extractText())
 
@@ -100,11 +100,11 @@
 
 ### WEB REQUESTS
 ## get request for https://jsonplaceholder.typicode.com/posts // https://jsonplaceholder.typicode.com/ 
-r = requests.get('https://jsonplaceholder.typicode.com/posts') ## get request
+r = requests.get('https://jsonplaceholder.typicode.com/users') ## get request
 ## load as json 
 r_data = r.json() ## load request as json
 ## load into dataframe
-df = pd.read_json(r_data) ## read json file
+df = pd.read_json(r_data, orient='records') ## read json file
 
 
 ### SQLALCHEMY
@@ -158,3 +158,4 @@
 results = query_job.result() ## get results
 ## putresults into dataframe
 df = pd.DataFrame(results.to_dataframe()) ## put results into dataframe
+df.columns
diff --git a/transformation/dataFiles/DHS_-_Hospitals_Locations_-_National.xls b/transformation/dataFiles/DHS_-_Hospitals_Locations_-_National.xls
diff --git a/transformation/dataFiles/raw/113243405_StonyBrookUniversityHospital_standardcharges.csv b/transformation/dataFiles/raw/113243405_StonyBrookUniversityHospital_standardcharges.csv
diff --git a/transformation/dataFiles/raw/131624096_mount-sinai-hospital_standardcharges.csv b/transformation/dataFiles/raw/131624096_mount-sinai-hospital_standardcharges.csv
diff --git a/transformation/dataFiles/raw/ECMC_Charge_Master_2022.csv b/transformation/dataFiles/raw/ECMC_Charge_Master_2022.csv
Original file line number	Diff line number	Diff line change
Expand Up		@@ -8,3 +8,5 @@
		# ignore all .json files inside of ingestion/bigquery/
		ingestion/example_files/bigquery/*/.json
		ingestion/example_files/bigquery/*.json