initial commit

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,12 @@
+---
+title: Trainer4Xlsx
+emoji: 🔥
+colorFrom: yellow
+colorTo: green
+sdk: gradio
+sdk_version: 5.36.2
+app_file: app.py
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,82 @@
+import gradio as gr
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.pipeline import make_pipeline
+from sklearn.linear_model import LogisticRegression
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics import classification_report
+
+model = None
+X_test = None
+y_test = None
+
+def load_excel(file):
+    # Read Excel file
+    xls = pd.ExcelFile(file.name)
+    # Just take first sheet to get columns
+    df = pd.read_excel(xls, xls.sheet_names[0])
+    columns = list(df.columns)
+    return columns, xls.sheet_names
+
+def load_sheet(file, sheet_name):
+    xls = pd.ExcelFile(file.name)
+    df = pd.read_excel(xls, sheet_name)
+    return df.head().to_dict(), list(df.columns)
+
+def train_model(file, sheet_name, text_col, target_col):
+    global model, X_test, y_test
+    
+    xls = pd.ExcelFile(file.name)
+    df = pd.read_excel(xls, sheet_name)
+
+    # Drop rows with missing in selected columns
+    df = df[[text_col, target_col]].dropna()
+    
+    X = df[text_col].astype(str)
+    y = df[target_col].astype(str)
+    
+    # Split train/test for evaluation
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+    # Simple pipeline TFIDF + Logistic Regression
+    model = make_pipeline(TfidfVectorizer(), LogisticRegression(max_iter=200))
+    model.fit(X_train, y_train)
+
+    y_pred = model.predict(X_test)
+    report = classification_report(y_test, y_pred)
+    return report
+
+def predict_text(text):
+    global model
+    if model is None:
+        return "Please train the model first."
+    pred = model.predict([text])
+    return pred[0]
+
+with gr.Blocks() as demo:
+    gr.Markdown("## Upload Excel training file")
+    upload = gr.File(label="Upload XLSX file")
+
+    cols_dropdown = gr.Dropdown(label="Select Category Column for Training")
+    sheet_dropdown = gr.Dropdown(label="Select Sheet", interactive=True)
+    
+    train_btn = gr.Button("Train Model")
+    output_train = gr.Textbox(label="Training Report", lines=10)
+
+    text_input = gr.Textbox(label="Text to Classify")
+    predict_btn = gr.Button("Predict")
+    output_pred = gr.Textbox(label="Prediction")
+
+    # When file uploaded, populate sheets dropdown
+    upload.change(lambda f: load_excel(f), inputs=upload, outputs=[cols_dropdown, sheet_dropdown])
+
+    # When sheet selected, load sheet to get columns for text + target
+    sheet_dropdown.change(lambda f, s: load_sheet(f, s), inputs=[upload, sheet_dropdown], outputs=[output_train, cols_dropdown])
+
+    # When train clicked, train the model using selected columns
+    train_btn.click(train_model, inputs=[upload, sheet_dropdown, cols_dropdown, cols_dropdown], outputs=output_train)
+
+    # Predict button
+    predict_btn.click(predict_text, inputs=text_input, outputs=output_pred)
+
+demo.launch()

requirements.txt

@@ -0,0 +1,7 @@
+gradio>=3.0
+pandas>=1.3
+scikit-learn>=1.0
+openpyxl>=3.0
+transformers>=4.0
+datasets>=2.0
+torch>=1.12