hpos-data/scripts/consolidated_data.py

import os
import firebase_admin
from firebase_admin import credentials
from firebase_admin import firestore
from google.cloud.firestore_v1.base_query import FieldFilter
import pandas as pd
# import datetime
import sys
import platform
from datetime import datetime, timedelta

environment = "preprod"

if __name__ == "__main__":

    if platform.system() == 'Windows':
        path_delim = '\\'
    else:
        path_delim = '/'
    
    key_file_path = os.getcwd() + path_delim + "keys" + path_delim + f"hpos-{environment}-firebase-adminsdk.json"
    cred = credentials.Certificate(key_file_path)  # Replace with your own service account key path
    firebase_admin.initialize_app(cred)

    # Get a reference to the Firestore database
    db = firestore.client()

    # Specify the collections
    patient_collection = db.collection("patientData")
    test_collection = db.collection("testData")
    start_date = sys.argv[1] # '2023-01-12' #input("Please enter the start date (yyyy-mm-dd): ")
    end_date = sys.argv[2] #'2023-07-16' #input("Please enter the end date (yyyy-mm-dd): ")

    # if start_date == end_date:
    #     start_date = datetime.strptime(start_date, "%Y-%m-%d")
    #     end_date = (start_date + timedelta(days=1)).strftime("%Y-%m-%d")

    print("end_date", end_date)

    # patient_collection = db.collection("patientData")
    query = db.collection("testData").where(filter=FieldFilter("testTime", ">=", start_date)).where(filter=FieldFilter("testTime", "<", end_date))

    # query = test_collection
    # patient_docs = query.stream()

    data = []
    # for patient_doc in patient_docs:
    #     patient_data = patient_doc.to_dict()
    #     patient_id = patient_data["_id"]

    #     test_docs = test_collection.where("_id", "==", patient_id).stream()

    #     for test_doc in test_docs:
    #         test_data = test_doc.to_dict()

    #         combined_data = {**patient_data, **test_data}

    #         for key, value in combined_data.items():
    #             if value == "" and key in patient_data:
    #                 combined_data[key] = patient_data[key]

    #         data.append(combined_data)

    test_docs = query.stream()
    for test_doc in test_docs:
        test_data = test_doc.to_dict()
        data.append(test_data)

    # Convert the data to a DataFrame
    df = pd.DataFrame(data)
    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)

    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 = df[(df['testTime'] > start_date) & (df['testTime'] <= end_date)]
    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", "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()

    print(f"Data saved to '{output_path}'")

    # Close the Firebase Admin SDK
    firebase_admin.delete_app(firebase_admin.get_app())