smiuser/hpos-data
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update data download fun

Browse Source
This commit is contained in:
Pritimay Sarkar
2024-02-10 20:25:25 +05:30
parent 283de77d37
commit c9dc69dffa
1 changed files with 7 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
cloud-functions/python/functions/consolidation/main.py
View File

@@ -66,35 +66,24 @@ def consolidation(request):
test_data = test_doc.to_dict()
data.append(test_data)
test_df = pd.DataFrame(data)
df = pd.DataFrame(data)
query = db.collection("patientData").where(filter=FieldFilter("createdAt", ">=", start_date)).where(filter=FieldFilter("createdAt", "<", end_date))
data = []
docs = query.stream()
for doc in docs:
row_data = doc.to_dict()
data.append(row_data)
user_df = pd.DataFrame(data)
df = pd.merge(test_df, user_df, on='_id')
output_filename = f'data_{datetime.today().strftime("%d_%m_%Y_%H_%M")}.xlsx'
output_filename = f'/tmp/data_{datetime.today().strftime("%d_%m_%Y_%H_%M")}.xlsx'
output_path = os.getcwd() + path_delim + output_filename
writer = pd.ExcelWriter(output_path, engine = 'openpyxl')
df = df[(df['testTime'] > start_date) & (df['testTime'] <= end_date)]
df = df.sort_values(by=['testTime'], ascending=False)
column_names = ["_id", "classificationResult", "deviceRatioClass", "prdClassification", "slopeRatioClass", "predictedDenovixRatio", "slopeRatio", "calculatedRatio", "deviceRatio", "kitSerial", "led1Gain1", "led1Gain2", "led1Gain4", "abs1", "led1Average", "led1Buffer", "led1Sample", "led2Gain1", "led2Gain2", "led2Gain4", "abs2", "led2Average", "led2Buffer", "led2Sample", "led3Gain1", "led3Gain2", "led3Gain4", "hb3", "abs3", "led3Average", "led3Buffer", "led3Sample", "led4Gain1", "led4Gain2", "led4Gain4", "hb4", "abs4", "led4Average", "led4Average", "led4Buffer", "led4Sample", "batteryLevel", "batteryVoltage", "solution", "concentration", "volume", "errorMessages", "deviceId", "deviceSerialNumber", "appVersion", "name_y", "testTime"]
column_names = ["_id", "classificationResult", "deviceRatioClass", "prdClassification", "slopeRatioClass", "predictedDenovixRatio", "slopeRatio", "calculatedRatio", "deviceRatio", "kitSerial", "led1Gain1", "led1Gain2", "led1Gain4", "abs1", "led1Average", "led1Buffer", "led1Sample", "led2Gain1", "led2Gain2", "led2Gain4", "abs2", "led2Average", "led2Buffer", "led2Sample", "led3Gain1", "led3Gain2", "led3Gain4", "hb3", "abs3", "led3Average", "led3Buffer", "led3Sample", "led4Gain1", "led4Gain2", "led4Gain4", "hb4", "abs4", "led4Average", "led4Average", "led4Buffer", "led4Sample", "batteryLevel", "batteryVoltage", "solution", "concentration", "volume", "errorMessages", "deviceId", "deviceSerialNumber", "appVersion", "name", "testTime"]
common_columns = [col for col in column_names if col in df.columns]
df = df[common_columns]
df.rename(columns={'deviceSerialNumber': "loginId", "name_y": "name"}, inplace = True)
# df = df.reindex(sorted(df.columns), axis=1)
df = df.drop_duplicates()
df.rename(columns={'deviceSerialNumber': "loginId"}, inplace = True)
# df = df.reindex(sorted(df.columns), axis=1)
df = df.drop_duplicates()
df.to_excel(writer, sheet_name = 'data', index=False)
writer.close()