Create salesforce_ocr_patient_registration.py

salesforce_ocr_patient_registration.py

@@ -0,0 +1,200 @@
+import os
+from paddleocr import PaddleOCR
+from PIL import Image
+import gradio as gr
+import requests
+import re
+from simple_salesforce import Salesforce
+import pandas as pd
+import matplotlib.pyplot as plt
+from io import BytesIO
+import kaleido
+
+# Attribute mappings: readable names to Salesforce API names
+ATTRIBUTE_MAPPING = {
+    "Name": "Name__c",
+    "Age": "Age__c",
+    "Gender": "Gender__c",
+    "Phone Number": "Phone__c"
+}
+
+# Salesforce credentials
+SALESFORCE_USERNAME = "[email protected]"
+SALESFORCE_PASSWORD = "HMS@2025"
+SALESFORCE_SECURITY_TOKEN = "5W0grfOaOxM9ocl3zYDgZ5CF"
+
+# Initialize PaddleOCR
+ocr = PaddleOCR(use_angle_cls=True, lang='en')
+
+# Function to extract text using PaddleOCR
+def extract_text(image):
+    result = ocr.ocr(image)
+    extracted_text = []
+    for line in result[0]:
+        extracted_text.append(line[1][0])
+    return "\n".join(extracted_text)
+
+# Function to extract attributes and their values
+def extract_attributes(extracted_text):
+    attributes = {}
+
+    # Patterns for extracting personal information
+    patterns = {
+        "Name": r"Name[:\-]?\s*([A-Za-z\s]+)",
+        "Age": r"Age[:\-]?\s*(\d{1,3})",
+        "Gender": r"Gender[:\-]?\s*(Male|Female|Other)",
+        "Phone Number": r"Phone[:\-]?\s*(\+?\d{10,12})"
+    }
+
+    for readable_attr, pattern in patterns.items():
+        match = re.search(pattern, extracted_text, re.IGNORECASE)
+        if match:
+            attributes[readable_attr] = match.group(1).strip()
+
+    return attributes
+
+# Function to filter attributes for valid Salesforce fields
+def filter_valid_attributes(attributes, valid_fields):
+    return {ATTRIBUTE_MAPPING[key]: value for key, value in attributes.items() if ATTRIBUTE_MAPPING[key] in valid_fields}
+
+# Function to interact with Salesforce
+def interact_with_salesforce(attributes):
+    try:
+        sf = Salesforce(
+            username=SALESFORCE_USERNAME,
+            password=SALESFORCE_PASSWORD,
+            security_token=SALESFORCE_SECURITY_TOKEN
+        )
+
+        object_name = "Patient_Registration__c"  # Using custom Patient Registration object
+        sf_object = sf.__getattr__(object_name)
+        schema = sf_object.describe()
+        valid_fields = {field["name"] for field in schema["fields"]}
+
+        filtered_attributes = filter_valid_attributes(attributes, valid_fields)
+
+        # Create a new record in Salesforce
+        result = sf_object.create(filtered_attributes)
+        return f"✅ Successfully created Patient Registration record with ID: {result['id']}."
+
+    except Exception as e:
+        return f"❌ Error interacting with Salesforce: {str(e)}"
+
+# Function to process image and extract attributes
+def process_image(image):
+    extracted_text = extract_text(image)
+    if not extracted_text:
+        return "No text detected in the image.", None, None
+
+    attributes = extract_attributes(extracted_text)
+
+    # Ensure all attributes are present, even if empty
+    for attr in ATTRIBUTE_MAPPING.keys():
+        if attr not in attributes:
+            attributes[attr] = ""
+
+    # Convert attributes to DataFrame for editing
+    df = pd.DataFrame(list(attributes.items()), columns=["Attribute", "Value"])
+    return f"Extracted Text:\n{extracted_text}", df, None
+
+# Function to handle edited attributes and export to Salesforce
+def export_to_salesforce(edited_df):
+    try:
+        # Convert edited DataFrame back to dictionary
+        edited_attributes = dict(zip(edited_df["Attribute"], edited_df["Value"]))
+
+        # Export to Salesforce
+        message = interact_with_salesforce(edited_attributes)
+        return message
+
+    except Exception as e:
+        return f"❌ Error exporting to Salesforce: {str(e)}"
+
+# Function to pull structured data from Salesforce and display as a table
+def pull_data_from_salesforce():
+    try:
+        sf = Salesforce(
+            username=SALESFORCE_USERNAME,
+            password=SALESFORCE_PASSWORD,
+            security_token=SALESFORCE_SECURITY_TOKEN
+        )
+
+        query = "SELECT Name__c, Age__c, Gender__c, Phone__c FROM Patient_Registration__c WHERE Age__c != NULL LIMIT 100"
+        response = sf.query_all(query)
+        records = response.get("records", [])
+
+        if not records:
+            return "No data found in Salesforce.", None, None, None
+
+        df = pd.DataFrame(records)
+        df = df.drop(columns=['attributes'], errors='ignore')
+
+        # Rename columns for better readability
+        df.rename(columns={
+            "Name__c": "Name",
+            "Age__c": "Age",
+            "Gender__c": "Gender",
+            "Phone__c": "Phone Number"
+        }, inplace=True)
+
+        excel_path = "salesforce_patient_registration.xlsx"
+        df.to_excel(excel_path, index=False)
+
+        # Generate a bar graph for age distribution
+        fig, ax = plt.subplots(figsize=(12, 8))
+        df['Age'] = pd.to_numeric(df['Age'], errors='coerce')
+        df.groupby('Age').size().plot(kind='bar', ax=ax)
+        ax.set_title("Age Distribution of Patient Registrations")
+        ax.set_xlabel("Age")
+        ax.set_ylabel("Number of Patients")
+        plt.xticks(rotation=45, ha="right", fontsize=10)
+        plt.tight_layout()
+        buffer = BytesIO()
+        plt.savefig(buffer, format="png")
+        buffer.seek(0)
+        img = Image.open(buffer)
+
+        return df, excel_path, img
+
+    except Exception as e:
+        return f"Error fetching data: {str(e)}", None, None, None
+
+# Gradio Interface
+def app():
+    with gr.Blocks() as demo:
+        with gr.Tab("📥 OCR Processing"):
+            with gr.Row():
+                image_input = gr.Image(type="numpy", label="📄 Upload Image")
+            extract_button = gr.Button("Extract Text and Attributes")
+            extracted_text_output = gr.Text(label="📝 Extracted Image Data")
+            editable_df_output = gr.Dataframe(label="✏️ Edit Attributes (Key-Value Pairs)", interactive=True)
+            ok_button = gr.Button("OK")
+            result_output = gr.Text(label="🚀 Result")
+
+        with gr.Tab("📊 Salesforce Data"):
+            pull_button = gr.Button("Pull Data from Salesforce")
+            salesforce_data_output = gr.Dataframe(label="📊 Salesforce Data")
+            excel_download_output = gr.File(label="📥 Download Excel")
+            graph_output = gr.Image(label="📈 Age Distribution Graph")
+
+        # Define button actions
+        extract_button.click(
+            fn=process_image,
+            inputs=[image_input],
+            outputs=[extracted_text_output, editable_df_output, result_output]
+        )
+        ok_button.click(
+            fn=export_to_salesforce,
+            inputs=[editable_df_output],
+            outputs=[result_output]
+        )
+        pull_button.click(
+            fn=pull_data_from_salesforce,
+            inputs=[],
+            outputs=[salesforce_data_output, excel_download_output, graph_output]
+        )
+
+    return demo
+
+if __name__ == "__main__":
+    app().launch(share=True)