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

drop duplicates in test data

Browse Source
This commit is contained in:
Pritimay Sarkar
2023-12-10 13:49:59 +05:30
parent e5a14f61b0
commit 0b314e4964
1 changed files with 6 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
scripts/consolidated_data.py
View File

@@ -9,7 +9,7 @@ import sys
import platform
from datetime import datetime, timedelta
environment = "af3cc"
environment = "preprod"
if __name__ == "__main__":
@@ -71,6 +71,7 @@ if __name__ == "__main__":
print(df)
print(df.size)
# Save the DataFrame to a CSV file
output_filename = f'data_{environment}_{datetime.today().strftime("%d_%m_%Y_%H_%M")}.xlsx'
df.to_csv(output_filename, index=False)
@@ -81,9 +82,12 @@ if __name__ == "__main__":
df = df[(df['testTime'] > start_date) & (df['testTime'] <= end_date)]
df = df.sort_values(by=['testTime'], ascending=False)
df = df[["_id", "classificationResult", "prdClassification", "predictedDenovixRatio", "calculatedRatio", "deviceRatio", "kitSerial", "abs1", "led1Average", "led1Buffer", "led1Sample", "abs2", "led2Average", "led2Buffer", "led2Sample", "abs3", "led3Average", "led3Buffer", "led3Sample", "abs4", "led4Average", "led4Buffer", "led4Sample", "batteryLevel", "batteryVoltage", "deviceId", "deviceSerialNumber", "name", "testTime"]]
df = df[["_id", "errorMessages", "classificationResult", "prdClassification", "predictedDenovixRatio", "calculatedRatio", "deviceRatio", "kitSerial", "abs1", "led1Average", "led1Buffer", "led1Sample", "abs2", "led2Average", "led2Buffer", "led2Sample", "abs3", "led3Average", "led3Buffer", "led3Sample", "abs4", "led4Average", "led4Buffer", "led4Sample", "batteryLevel", "batteryVoltage", "deviceId", "deviceSerialNumber", "name", "testTime"]]
# df.rename(columns={'deviceSerialNumber': "login_id", "calculatedRatio": "calibrated_ratio", "led1Buffer": "427_buffer_intensity", "led2Buffer": "555_buffer_intensity", "led1Sample": "427_sample_intensity", "led2Sample": "555_sample_intensity", "led1Average": "427_absorbance", "led2Average": "555_absorbance"}, 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()