init

app.py

@@ -0,0 +1,143 @@
+import gradio as gr
+from pandasai_tool import pandas_ai_res
+import time
+
+# import csv or xlsx file and use input as df
+# pandas_ai_res function will return resultr
+with gr.Blocks() as demo:
+    gr.Label("🗣말로 하는 데이터 분석")
+    gr.Markdown("(안내) 데이터 파일을 업로드하고, 분석을 부탁하세요")
+    # uploaded_file = gr.File(label="파일 업로드")
+    # chatbot = gr.Chatbot()
+    # msg = gr.Textbox()
+    # clear = gr.ClearButton([msg, chatbot], label="채팅 기록 삭제")
+    #
+    # def respond(file, message, chat_history):
+    #     bot_message = pandas_ai_res(file, message)
+    #     chat_history.append((message, bot_message))
+    #     # time.sleep(2)
+    #     return "", chat_history
+    #
+    # msg.submit(respond, [uploaded_file, msg, chatbot], [msg, chatbot])
+
+    gr.Interface(
+        fn=pandas_ai_res,
+        inputs=["file", "text"],
+        outputs="text"
+    )
+
+if __name__ == "__main__":
+    demo.launch(share=True)
+
+#
+# import gradio as gr
+# import pandas as pd
+# from huggingface_hub.hf_api import create_repo, upload_file, HfApi
+# from huggingface_hub.repository import Repository
+# import subprocess
+# import os
+# import tempfile
+#
+#
+# import sweetviz as sv
+#
+#
+# def analyze_datasets(dataset, dataset_name, token, column=None, pairwise="off"):
+#     df = pd.read_csv(dataset.name)
+#     username = HfApi().whoami(token=token)["name"]
+#     if column is not None:
+#         analyze_report = sv.analyze(df, target_feat=column, pairwise_analysis=pairwise)
+#     else:
+#         analyze_report = sv.analyze(df, pairwise_analysis=pairwise)
+#     analyze_report.show_html('./index.html', open_browser=False)
+#     repo_url = create_repo(f"{username}/{dataset_name}", repo_type="space", token=token, space_sdk="static",
+#                            private=False)
+#
+#     upload_file(path_or_fileobj="./index.html", path_in_repo="index.html", repo_id=f"{username}/{dataset_name}",
+#                 repo_type="space", token=token)
+#     readme = f"---\ntitle: {dataset_name}\nemoji: ✨\ncolorFrom: green\ncolorTo: red\nsdk: static\npinned: false\ntags:\n- dataset-report\n---"
+#     with open("README.md", "w+") as f:
+#         f.write(readme)
+#     upload_file(path_or_fileobj="./README.md", path_in_repo="README.md", repo_id=f"{username}/{dataset_name}",
+#                 repo_type="space", token=token)
+#
+#     return f"Your dataset report will be ready at {repo_url}"
+#
+#
+#
+#
+#
+#
+# with gr.Blocks() as demo:
+#     main_title = gr.Markdown("""# Easy Analysis🪄🌟✨""")
+#     main_desc = gr.Markdown(
+#         """This app enables you to run three type of dataset analysis and pushes the interactive reports to your Hugging Face Hub profile as a Space. It uses SweetViz in the back.""")
+#     with gr.Tabs():
+#         with gr.TabItem("Analyze") as analyze:
+#             with gr.Row():
+#                 with gr.Column():
+#                     title = gr.Markdown(""" ## Analyze Dataset """)
+#                     description = gr.Markdown(
+#                         "Analyze a dataset or predictive variables against a target variable in a dataset (enter a column name to column section if you want to compare against target value). You can also do pairwise analysis, but it has quadratic complexity.")
+#                     dataset = gr.File(label="Dataset")
+#                     column = gr.Text(label="Compare dataset against a target variable (Optional)")
+#                     pairwise = gr.Radio(["off", "on"], label="Enable pairwise analysis")
+#                     token = gr.Textbox(label="Your Hugging Face Token")
+#                     dataset_name = gr.Textbox(label="Dataset Name")
+#                     pushing_desc = gr.Markdown(
+#                         "This app needs your Hugging Face Hub token and a unique name for your dataset report.")
+#                     inference_run = gr.Button("Infer")
+#                     inference_progress = gr.StatusTracker(cover_container=True)
+#                 outcome = gr.outputs.Textbox()
+#                 inference_run.click(
+#                     analyze_datasets,
+#                     inputs=[dataset, dataset_name, token, column, pairwise],
+#                     outputs=outcome,
+#                     status_tracker=inference_progress,
+#                 )
+#         with gr.TabItem("Compare Splits") as compare_splits:
+#             with gr.Row():
+#                 with gr.Column():
+#                     title = gr.Markdown(""" ## Compare Splits""")
+#                     description = gr.Markdown(
+#                         "Split a dataset and compare splits. You need to give a fraction, e.g. 0.8.")
+#                     dataset = gr.File(label="Dataset")
+#                     split_ratio = gr.Number(label="Split Ratios")
+#                     pushing_desc = gr.Markdown(
+#                         "This app needs your Hugging Face Hub token and a unique name for your dataset report.")
+#                     token = gr.Textbox(label="Your Hugging Face Token")
+#                     dataset_name = gr.Textbox(label="Dataset Name")
+#                     inference_run = gr.Button("Infer")
+#                     inference_progress = gr.StatusTracker(cover_container=True)
+#
+#                 outcome = gr.outputs.Textbox()
+#                 inference_run.click(
+#                     compare_dataset_splits,
+#                     inputs=[dataset, dataset_name, token, split_ratio],
+#                     outputs=outcome,
+#                     status_tracker=inference_progress,
+#                 )
+#
+#         with gr.TabItem("Compare Subsets") as compare_subsets:
+#             with gr.Row():
+#                 with gr.Column():
+#                     title = gr.Markdown(""" ## Compare Subsets""")
+#                     description = gr.Markdown(
+#                         "Compare subsets of a dataset, e.g. you can pick Age Group column and compare adult category against young.")
+#                     dataset = gr.File(label="Dataset")
+#                     column = gr.Text(label="Enter column:")
+#                     category = gr.Text(label="Enter category:")
+#                     pushing_desc = gr.Markdown(
+#                         "This app needs your Hugging Face Hub token and a unique name for your dataset report.")
+#                     token = gr.Textbox(label="Your Hugging Face Token")
+#                     dataset_name = gr.Textbox(label="Dataset Name")
+#                     inference_run = gr.Button("Run Analysis")
+#                     inference_progress = gr.StatusTracker(cover_container=True)
+#
+#                 outcome = gr.outputs.Textbox()
+#                 inference_run.click(
+#                     compare_column_values,
+#                     inputs=[dataset, dataset_name, token, column, category],
+#                     outputs=outcome,
+#                     status_tracker=inference_progress,
+#                 )

pandasai_tool.py

@@ -0,0 +1,47 @@
+from pandasai import SmartDataframe
+import pandas as pd
+from pandasai.llm.google_gemini import GoogleGemini
+
+# df = pd.DataFrame({
+#     "country": [
+#         "United States",
+#         "United Kingdom",
+#         "France",
+#         "Germany",
+#         "Italy",
+#         "Spain",
+#         "Canada",
+#         "Australia",
+#         "Japan",
+#         "China",
+#     ],
+#     "gdp": [
+#         19294482071552,
+#         2891615567872,
+#         2411255037952,
+#         3435817336832,
+#         1745433788416,
+#         1181205135360,
+#         1607402389504,
+#         1490967855104,
+#         4380756541440,
+#         14631844184064,
+#     ],
+#     "happiness_index": [6.94, 7.16, 6.66, 7.07, 6.38, 6.4, 7.23, 7.22, 5.87, 5.12],
+# })
+llm = GoogleGemini(api_key="AIzaSyCW-TP3IlbbdQmp_nDMEEaip0uVcK9lbgA")
+
+def pandas_ai_res(file, input_text, llm=llm):
+    # check if the file is csv or xlsx
+    if file.name.endswith(".csv"):
+        df = pd.read_csv(file.name)
+    elif file.name.endswith(".xlsx"):
+        df = pd.read_excel(file.name)
+
+    sdf = SmartDataframe(df, config={"llm": llm})
+
+    return sdf.chat(input_text)
+
+
+# sdf = SmartDataframe(df, config={"llm": llm})
+# sdf.chat("Return the top 5 countries by GDP")