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

chnage pref name

Browse Source
This commit is contained in:
Pritimay Sarkar
2024-01-16 15:29:30 +05:30
parent 7917d5073b
commit 6f4ba44e48
7 changed files with 107 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
scripts/test_collection.py
View File

@@ -30,12 +30,11 @@ df = pd.DataFrame(data)
print(df)
print(df.size)
# 4 abs
#df = df[["_id", "batteryLevel", "batteryVoltage", "classificationResult", "prdClassification", "predictedDenovixRatio", "calculatedRatio", "deviceRatio", "kitSerial", "abs1", "led1Average", "led1Buffer", "led1Sample", "abs2", "led2Average", "led2Buffer", "led2Sample", "abs3", "led3Average", "led3Buffer", "led3Sample", "abs4", "led4Average", "led4Buffer", "led4Sample", "deviceId", "deviceSerialNumber", "name", "testTime"]]
# 2 abs
#df = df[["_id", "finalResult", "classificationResult", "calculatedRatio", "deviceRatio", "kitSerial", "led1Average", "led1Buffer", "led1Sample", "led2Average", "led2Buffer", "led2Sample", "deviceId", "deviceSerialNumber", "name", "testTime"]]
df = df[["_id", "classificationResult", "calculatedRatio", "deviceRatio", "kitSerial", "led1Average", "led1Buffer", "led1Sample", "led2Average", "led2Buffer", "led2Sample", "deviceId", "deviceSerialNumber", "name", "testTime"]]
column_names = ["_id", "name", "classificationResult", "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", "deviceId", "deviceSerialNumber", "appVersion", "testTime"]
common_columns = [col for col in column_names if col in df.columns]
df = df[common_columns]
print("duplicates", len(df['_id']) - len(df['_id'].drop_duplicates()))
@@ -63,7 +62,8 @@ downloads_dir = os.path.join(os.path.expanduser("~"), "Downloads")
output_path = os.path.join(downloads_dir, output_filename)
writer = pd.ExcelWriter(output_path, engine = 'openpyxl')
df.to_excel(writer, sheet_name = 'data', index=False)
df_count.to_excel(writer, sheet_name = "count")
df_count.to_excel(writer, sheet_name = "hc_count")
df.groupby(["result"]).describe()["resultRatio"]["count"].to_excel(writer, sheet_name = "tr_count")
df.groupby(["deviceId"]).describe().to_excel(writer, sheet_name = "stats")
df.groupby(["kitSerial"]).describe()["calculatedRatio"]["count"].to_excel(writer, sheet_name = "kit_count")
df.groupby(["kitSerial", "classificationResult"]).describe()["calculatedRatio"]["count"].to_excel(writer, sheet_name = "kit_class")