first commit

app.py

@@ -0,0 +1,73 @@
+import nltk
+from bs4 import BeautifulSoup
+import joblib
+import gradio as gr
+
+classes = ['.net', 'android', 'asp.net', 'c', 'c#', 'c++', 'css', 'html',
+           'ios', 'iphone', 'java', 'javascript', 'jquery', 'json', 'linux',
+           'mysql', 'node.js', 'objective-c', 'performance', 'php', 'python',
+           'reactjs', 'ruby-on-rails', 'spring', 'sql', 'sql-server', 'swift',
+           'unit-testing', 'windows', 'xcode']
+
+pa_classifier = joblib.load("passive_aggressive_classifier.pkl")
+tfidf_vectorizer = joblib.load("tfidf_vectorizer.pkl")
+
+def run(text: str):
+    text = clean_input_string(text)
+    vectors = get_tf_idf_vectors([text])
+    prediction_list = pa_classifier.predict(vectors)[0]
+    predicted_classes = [classes[i] for i, pred in enumerate(prediction_list) if pred == 1]
+    if predicted_classes:
+        return " ".join(predicted_classes)
+    return "Pas de thème retrouvé."
+
+
+
+def get_tf_idf_vectors(x_as_string):
+    return tfidf_vectorizer.transform(x_as_string)
+def clean_input_string(text: str) -> str:
+    text = remove_escape_sequences(text)
+    text = remove_html_tags(text)
+    text_as_list = remove_punctuation(text)
+    text_as_list = remove_stopwords(text_as_list)
+    text_as_list = lemmatize(text_as_list)
+    return " ".join(text_as_list)
+
+
+def remove_escape_sequences(text: str):
+    return text.encode('unicode-escape').decode('utf-8').replace('\\n', '').replace('\\t', '').replace('\\r', '').replace('\\\\', '').replace('\\\'', '').replace('\"', '')
+
+
+def remove_html_tags(text: str):
+    soup = BeautifulSoup(text, 'html.parser')
+    return soup.get_text()
+
+
+def remove_punctuation(text: str):
+    tokenizer = nltk.RegexpTokenizer(r'[a-zA-Z]+')
+    text = text.lower()
+    return tokenizer.tokenize(text)
+
+
+
+def remove_stopwords(words_list: list):
+    sw = set()
+    sw.update(tuple(nltk.corpus.stopwords.words('english')))
+    return [word for word in words_list if word not in sw]
+
+
+def lemmatize(words_list: list):
+    lemmatizer = nltk.WordNetLemmatizer()
+    return [lemmatizer.lemmatize(word) for word in words_list]
+
+
+def greet(name, intensity):
+    return "Hello, " + name + "!" * int(intensity)
+
+demo = gr.Interface(
+    fn=run,
+    inputs=["text"],
+    outputs=["text"],
+)
+
+demo.launch()