This commit is contained in:
Pritimay Sarkar
2023-08-17 21:37:31 +05:30
4 changed files with 339 additions and 0 deletions

View File

@@ -0,0 +1,146 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"id": "edbb2bd6-e678-4401-9c0d-83d9ad948bb7",
"metadata": {},
"outputs": [],
"source": [
"import csv\n",
"\n",
"def copy_columns(source_file, destination_file, header_names):\n",
" with open(source_file, 'r', newline='') as source_csvfile, open(destination_file, 'w', newline='') as destination_csvfile:\n",
" reader = csv.DictReader(source_csvfile)\n",
" fieldnames = header_names\n",
" writer = csv.DictWriter(destination_csvfile, fieldnames=fieldnames)\n",
"\n",
" writer.writeheader()\n",
"\n",
" for row in reader:\n",
" selected_data = {key: row[key] for key in fieldnames if key in row}\n",
" writer.writerow(selected_data)\n",
"\n",
"if __name__ == \"__main__\":\n",
" source_csv = \"path/to/source_file.csv\" # Replace with the path to your source CSV file\n",
" destination_csv = \"path/to/destination_file.csv\" # Replace with the path to your destination CSV file\n",
" header_names = [\"Name\", \"ABHA ID\", \"Age\", \"Gender\", \"Category\", \"Marital Status\", \"Care-of\", \"Address\", \"District\", \"State\", \"Pincode\", \"Mobile Number\", \"Blood group\", \"Test Result\"] # Replace with the header names you want to copy\n",
"\n",
" copy_columns(source_csv, destination_csv, header_names)\n",
"\n",
" print(\"Data copied successfully.\")\n"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "c242e21e-48a9-462c-8e3f-453913f84564",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Data copied successfully with new header.\n"
]
}
],
"source": [
"import csv\n",
"from datetime import datetime\n",
"\n",
"def calculate_age(birth_year):\n",
" current_year = datetime.now().year\n",
" return current_year - birth_year\n",
"\n",
"def copy_csv_with_new_header(source_file, destination_file, destination_header):\n",
" # Create a list to store the filtered data from the source CSV file\n",
" temp_data = []\n",
"\n",
" # Create a mapping for the destination header names to the source header names\n",
" header_mapping = {\n",
" \"Name\": \"name\",\n",
" \"ABHA ID\": \"abhaId\",\n",
" \"Age\": \"birthYear\",\n",
" \"Gender\": \"gender\",\n",
" \"Category\": \"category\",\n",
" \"Marital Status\": \"maritalStatus\",\n",
" \"Care-of\": \"careOf\",\n",
" \"Address\": \"house\",\n",
" \"District\": \"district\",\n",
" \"State\": \"state\",\n",
" \"Pincode\": \"pinCode\",\n",
" \"Mobile Number\": \"phoneNumber\",\n",
" \"Blood Group\": \"bloodGroup\",\n",
" \"Test Result\": \"Class\"\n",
" }\n",
"\n",
" with open(source_file, 'r', newline='') as source_csvfile:\n",
" reader = csv.DictReader(source_csvfile)\n",
"\n",
" # Read the data from the source CSV file\n",
" for row in reader:\n",
" # Assuming the column \"birthYear\" exists in the CSV\n",
" birth_year = int(row.get(\"birthYear\", 0))\n",
" updated_age = calculate_age(birth_year)\n",
"\n",
" # Filter out unwanted fields from the row based on the destination header\n",
" filtered_row = {key: row[header_mapping[key]] if key != \"Age\" else updated_age for key in destination_header}\n",
"\n",
" # Add the filtered row to the temporary data list\n",
" temp_data.append(filtered_row)\n",
"\n",
" with open(destination_file, 'w', newline='') as destination_csvfile:\n",
" writer = csv.DictWriter(destination_csvfile, fieldnames=destination_header)\n",
"\n",
" # Write the new header to the destination CSV file\n",
" writer.writeheader()\n",
"\n",
" # Write the updated data to the destination CSV file\n",
" writer.writerows(temp_data)\n",
"\n",
"if __name__ == \"__main__\":\n",
" source_csv = r\"C:\\Users\\Durga\\Desktop\\from27.csv\" # Replace with the path to your source CSV file\n",
"\n",
" # Replace with the destination header names you want in the new CSV\n",
" destination_header = [\"Name\", \"ABHA ID\", \"Age\", \"Gender\", \"Category\", \"Marital Status\", \"Care-of\", \"Address\", \n",
" \"District\", \"State\", \"Pincode\", \"Mobile Number\", \"Blood Group\", \"Test Result\"]\n",
"\n",
" destination_csv = r\"C:\\Users\\Durga\\Desktop\\result tilljuly31.csv\" # Replace with the path to your destination CSV file\n",
"\n",
" copy_csv_with_new_header(source_csv, destination_csv, destination_header)\n",
"\n",
" print(\"Data copied successfully with new header.\")\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "965db908-c717-40a3-81cb-3da73b744ec5",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

Binary file not shown.

64
scripts/UserCollection.py Normal file
View File

@@ -0,0 +1,64 @@
import os
import firebase_admin
from IPython.core.display import Image
from IPython.core.display_functions import display
from firebase_admin import credentials
from firebase_admin import firestore
import pandas as pd
import datetime
print("pritimay")
# Initialize Firebase Admin SDK
cred = credentials.Certificate(r'C:\Users\smila\PycharmProjects\pythonProject\hpos-prod-firebase-adminsdk-bionp-5486f7becd.json') # 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 = input("Please enter the start date (yyyy-mm-dd): ")
end_date = input("Please enter the end date (yyyy-mm-dd): ")
query = patient_collection.where("createdAt", ">=", start_date).where("createdAt", "<", end_date)
patient_docs = query.stream()
# Prepare data to store in CSV
data = []
for patient_doc in patient_docs:
patient_data = patient_doc.to_dict()
patient_id = patient_data["_id"]
# Query the document from testData collection based on the common _id
test_docs = test_collection.where("_id", "==", patient_id).stream()
for test_doc in test_docs:
test_data = test_doc.to_dict()
# Combine the data from both collections into a single dictionary
combined_data = {**patient_data, **test_data}
# Skip if the csvPath is not a valid URL
data.append(combined_data)
# Convert the data to a DataFrame
df = pd.DataFrame(data)
print(df.size)
# Save the DataFrame to a CSV file
output_filename = "data.csv"
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)
df.to_csv(output_path, index=False)
print(f"Data saved to '{output_path}'")
# Close the Firebase Admin SDK
firebase_admin.delete_app(firebase_admin.get_app())

View File

@@ -0,0 +1,129 @@
import os
import firebase_admin
from firebase_admin import credentials, firestore
import pandas as pd
from urllib.request import urlopen
import datetime
import tkinter as tk
from tkinter import filedialog
# Initialize Firebase Admin SDK
cred = credentials.Certificate(r'C:\Users\smila\PycharmProjects\pythonProject\hpos-prod-firebase-adminsdk-bionp-5486f7becd.json') # 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")
# Create a tkinter root window (hidden)
root = tk.Tk()
root.withdraw()
# Ask the user to select the base folder where images and data will be saved
base_output_folder = filedialog.askdirectory(title="Select Base Output Folder")
# Get user-defined date ranges
start_date = "2023-08-01"
end_date = "2023-08-10"
# Parse the date range to get a list of days
start_datetime = datetime.datetime.strptime(start_date, "%Y-%m-%d")
end_datetime = datetime.datetime.strptime(end_date, "%Y-%m-%d")
date_range = [start_datetime + datetime.timedelta(days=x) for x in range((end_datetime - start_datetime).days + 1)]
# Iterate through each day
for date in date_range:
current_date = date.strftime("%Y-%m-%d")
output_folder = os.path.join(base_output_folder, current_date)
os.makedirs(output_folder, exist_ok=True)
print(f"Processing data for {current_date}...")
# Query Firestore for patient data
query = patient_collection.where("createdAt", ">=", current_date).where("createdAt", "<", (date + datetime.timedelta(days=1)).strftime("%Y-%m-%d"))
patient_docs = query.stream()
# Initialize a list to hold the combined data
data = []
# Iterate through patient documents
for patient_doc in patient_docs:
patient_data = patient_doc.to_dict()
patient_id = patient_data["_id"]
# Query the document from testData collection based on the common _id
test_docs = test_collection.where("_id", "==", patient_id).stream()
# Iterate through test documents
for test_doc in test_docs:
test_data = test_doc.to_dict()
# Combine the data from both collections into a single dictionary
combined_data = {**patient_data, **test_data}
# Access specific attributes from the combined data
csv_path = combined_data.get("csvPath", "")
if csv_path and not csv_path.startswith("http"):
# Perform the desired action
print("CSV path does not start with 'http'.")
# Append the combined_data dictionary to the list
data.append(combined_data)
# Download images separately and store them in the specified folder
user_image_url = combined_data.get("userImageURL", "")
if user_image_url and user_image_url.startswith("http"):
image_data = urlopen(user_image_url).read()
image_filename = f"{patient_id}.jpg" # Use only patient ID as the filename
image_path = os.path.join(output_folder, image_filename)
with open(image_path, "wb") as image_file:
image_file.write(image_data)
# Convert the data to a DataFrame
df = pd.DataFrame(data)
# Rename columns
df.rename(columns={
"name": "Name",
"abhaId": "ABHA ID",
"birthYear": "Age",
"gender": "Gender",
"category": "Category",
"maritalStatus": "Marital Status",
"careOf": "Care-of",
"city": "Address",
"district": "District",
"state": "State",
"pinCode": "Pincode",
"phoneNumber": "Mobile Number",
"bloodGroup": "Blood group",
"result": "Test Result"
}, inplace=True)
# Select specific columns
selected_columns = [
"Name", "ABHA ID", "Age", "Gender", "Category", "Marital Status",
"Care-of", "Address", "District", "State", "Pincode", "Mobile Number",
"Blood group", "Test Result"
]
# Check if selected columns are present in the DataFrame
missing_columns = [col for col in selected_columns if col not in df.columns]
if missing_columns:
print(f"Missing columns: {missing_columns}")
else:
# Create a new DataFrame with selected columns
df = df[selected_columns]
# Save the DataFrame to a CSV file
output_filename = f"data_{current_date}.csv"
output_path = os.path.join(output_folder, output_filename)
df.to_csv(output_path, index=False)
print(f"Data and images for {current_date} saved to '{output_folder}'")
# Close the Firebase Admin SDK
firebase_admin.delete_app(firebase_admin.get_app())