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

new common columns format

Browse Source
This commit is contained in:
Pritimay Sarkar
2024-01-15 21:04:53 +05:30
parent 4937b061ad
commit 7917d5073b
1 changed files with 7 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
scripts/consolidated_data.py
View File

@@ -9,7 +9,7 @@ import sys
import platform import platform
from datetime import datetime, timedelta from datetime import datetime, timedelta
environment = "qa" environment = "af3cc"
if __name__ == "__main__": if __name__ == "__main__":
@@ -69,7 +69,7 @@ if __name__ == "__main__":
# Convert the data to a DataFrame # Convert the data to a DataFrame
df = pd.DataFrame(data) df = pd.DataFrame(data)
print(df) print(df)
print(df.size) print(df.columns)
# Save the DataFrame to a CSV file # Save the DataFrame to a CSV file
@@ -81,8 +81,11 @@ if __name__ == "__main__":
writer = pd.ExcelWriter(output_path, engine = 'openpyxl') writer = pd.ExcelWriter(output_path, engine = 'openpyxl')
df = df[(df['testTime'] > start_date) & (df['testTime'] <= end_date)] df = df[(df['testTime'] > start_date) & (df['testTime'] <= end_date)]
df = df.sort_values(by=['testTime'], ascending=False) df = df.sort_values(by=['testTime'], ascending=False)
df = df[["_id", "errorMessages", "classificationResult", "prdClassification", "predictedDenovixRatio", "calculatedRatio", "deviceRatio", "kitSerial", "abs1", "led1Average", "led1Buffer", "led1Sample", "abs2", "led2Average", "led2Buffer", "led2Sample", "hb3", "abs3", "led3Average", "led3Buffer", "led3Sample", "hb4", "abs4", "led4Average", "led4Buffer", "led4Sample", "batteryLevel", "batteryVoltage", "deviceId", "deviceSerialNumber", "name", "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': "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.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.reindex(sorted(df.columns), axis=1)