Spaces:

sri8888
/

webapp

Runtime error

App Files Files Community

sri8888 commited on Jan 8, 2025

Commit

74d86cf

verified ·

1 Parent(s): 4a6d47a

Upload 2 files

Browse files

Files changed (2) hide show

Requirement.txt +6 -0
app.py +164 -0

Requirement.txt ADDED Viewed

	@@ -0,0 +1,6 @@

+gradio
+pandas
+scikit-learn
+openpyxl
+joblib
+pyarrow

app.py ADDED Viewed

	@@ -0,0 +1,164 @@

+import pandas as pd
+import gradio as gr
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
+from openpyxl import load_workbook
+from IPython.display import Markdown
+import os
+# Initialize empty DataFrame and TF-IDF matrix
+data = pd.DataFrame()
+tfidf_vectorizer = None
+tfidf_matrix = None
+# Helper: Load Data from File (Excel or CSV)
+def load_file(file):
+    global data, tfidf_vectorizer, tfidf_matrix
+    try:
+        # Read file based on its extension
+        if file.endswith(".xlsx"):
+            # Read Excel file
+            workbook = load_workbook(filename=file, data_only=True)
+            sheet = workbook.active
+            headers = [cell.value if cell.value is not None else f"Unnamed Column {i}" for i, cell in enumerate(sheet[1])]
+            rows = sheet.iter_rows(min_row=2, values_only=True)
+            data = pd.DataFrame(rows, columns=headers)
+            # Extract hyperlinks from "Information" column if present
+            if "Information" in data.columns:
+                for i, row in enumerate(sheet.iter_rows(min_row=2)):
+                    cell = row[data.columns.get_loc("Information")]
+                    if cell.hyperlink:
+                        data.at[i, "Information"] = cell.hyperlink.target
+        elif file.endswith(".csv"):
+            # Read CSV file
+            data = pd.read_csv(file)
+        else:
+            return "Unsupported file format. Please upload a .xlsx or .csv file."
+        # Initialize TF-IDF for employee search
+        tfidf_vectorizer = TfidfVectorizer(analyzer="char_wb", ngram_range=(2, 4))
+        tfidf_matrix = tfidf_vectorizer.fit_transform(data["Employee Name"].astype(str))
+        return "File loaded successfully!"
+    except Exception as e:
+        return f"Error loading file: {e}"
+# Helper: Generate Report Dynamically
+import os
+def generate_dynamic_report(query):
+    if data.empty or tfidf_vectorizer is None:
+        return None
+    query_vec = tfidf_vectorizer.transform([query])
+    similarities = cosine_similarity(query_vec, tfidf_matrix).flatten()
+    best_match_idx = similarities.argmax()
+    if similarities[best_match_idx] > 0:
+        employee = data.iloc[best_match_idx]
+        employee_name = employee["Employee Name"]
+        report_file = f"{employee_name.replace(' ', '_')}_report.html"
+        # Generate HTML content dynamically
+        with open(report_file, "w") as file:
+            file.write(f"<html><head><title>{employee_name} Report</title></head><body>")
+            file.write(f"<h1>Employee Report for {employee_name}</h1>")
+            file.write("<hr>")
+            # Employee Details
+            file.write("<h2>Employee Details:</h2><ul>")
+            for column, value in employee.items():
+                if column == "Information" and isinstance(value, str):
+                    if value.startswith("http") or value.startswith("file://"):
+                        # Detect file type from hyperlink
+                        file_type = os.path.splitext(value)[-1].lower()
+                        if file_type == ".pdf":
+                            label = "View PDF Document"
+                        elif file_type in [".ppt", ".pptx"]:
+                            label = "View PowerPoint Presentation"
+                        elif file_type in [".doc", ".docx"]:
+                            label = "View Word Document"
+                        else:
+                            label = "Download/View File"
+                        value = f'<a href="{value}" target="_blank" style="color:blue;text-decoration:underline;">{label}</a>'
+                    else:
+                        # Add a clickable link for local paths
+                        value = f'<a href="file:///{value}" target="_blank" style="color:blue;text-decoration:underline;">Download/View File</a>'
+                file.write(f"<li><strong>{column}:</strong> {value}</li>")
+            file.write("</ul>")
+            # Customer Insights
+            file.write("<h2>Customer Insights:</h2><ul>")
+            if "Experience" in data.columns:
+                experience = employee.get("Experience", "No experience details available.")
+                file.write(f"<li>Experience in the field: {experience}</li>")
+            if "Skills" in data.columns:
+                skills = employee.get("Skills", "No skills information available.")
+                file.write(f"<li>Key skills: {skills}</li>")
+            if "Projects" in data.columns:
+                projects = employee.get("Projects", "No projects listed.")
+                file.write(f"<li>Notable projects: {projects}</li>")
+            file.write("</ul>")
+            # Summary
+            file.write("<h2>Summary:</h2>")
+            file.write(f"<p>{employee_name} has shown notable contributions in the domain. Refer to the linked documents for more details.</p>")
+            file.write("<p>Thank you for using our Employee Dashboard!</p>")
+            file.write("</body></html>")
+        return report_file
+    else:
+        return None
+# Helper: Search Employee
+def search_employee(query):
+    if data.empty or tfidf_vectorizer is None:
+        return pd.DataFrame([{"Error": "No data available. Please upload a file first."}])
+    query_vec = tfidf_vectorizer.transform([query])
+    similarities = cosine_similarity(query_vec, tfidf_matrix).flatten()
+    best_match_idx = similarities.argmax()
+    if similarities[best_match_idx] > 0:
+        # Ensure output is a valid DataFrame with one row
+        employee = data.iloc[best_match_idx].to_frame().T  # Convert Series to DataFrame
+        return employee
+    else:
+        return pd.DataFrame([{"Error": "No matching employee found."}])
+# Gradio Interface
+with gr.Blocks() as interface:
+    gr.Markdown("""
+    <h1 style="text-align: center;">Employee Dashboard</h1>
+    <p style="text-align: center;">Upload your Excel or CSV file to get started. Search employees, view metrics, and generate dynamic reports.</p>
+    """)
+    with gr.Row():
+        file_upload = gr.File(label="Upload Excel or CSV File", type="filepath")
+        upload_status = gr.Textbox(label="Upload Status", interactive=False)
+    upload_button = gr.Button("Upload")
+    upload_button.click(load_file, inputs=[file_upload], outputs=[upload_status])
+    with gr.Row():
+        search_query = gr.Textbox(label="Search Employee", placeholder="Type partial name (e.g., 'Aar')")
+        employee_details = gr.Dataframe(label="Employee Details", interactive=True)
+        report_output = gr.File(label="Download Report")
+    search_button = gr.Button("Search")
+    search_button.click(
+        search_employee,
+        inputs=[search_query],
+        outputs=[employee_details],
+    )
+    search_button.click(
+        generate_dynamic_report,
+        inputs=[search_query],
+        outputs=[report_output],
+    )
+if __name__ == "__main__":
+    interface.launch(share=True)