Upload 2 files

app.py

@@ -0,0 +1,37 @@
+import gradio as gr
+from datasets import load_dataset
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.linear_model import LogisticRegression
+from sklearn.pipeline import Pipeline
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import classification_report
+
+# Загрузка датасета
+dataset = load_dataset("UniversalCEFR/cefr_sp_en", split="train")
+
+# Подготовка данных
+texts = [item['text'] for item in dataset if item['text']]
+labels = [item['cefr_level'] for item in dataset if item['text']]
+
+# Делим на тренировку и тест
+X_train, X_test, y_train, y_test = train_test_split(texts, labels, test_size=0.2, random_state=42)
+
+# Модель
+model = Pipeline([
+    ("tfidf", TfidfVectorizer(max_features=5000)),
+    ("clf", LogisticRegression(max_iter=1000))
+])
+model.fit(X_train, y_train)
+
+# Проверка
+print(classification_report(y_test, model.predict(X_test)))
+
+# Интерфейс Gradio
+def predict(text):
+    pred = model.predict([text])[0]
+    proba = model.predict_proba([text])[0]
+    confidence = round(max(proba) * 100, 2)
+    return f"Уровень: {pred} (уверенность: {confidence}%)"
+
+interface = gr.Interface(fn=predict, inputs="text", outputs="text", title="CEFR Level Estimator")
+interface.launch()

requirements.txt

@@ -0,0 +1,5 @@
+scikit-learn
+pandas
+matplotlib
+datasets
+gradio