Update main.py

main.py

@@ -1,74 +1,214 @@
-from flask import Flask, render_template, request, send_file
+from flask import Flask, render_template, request, jsonify, send_file
 from services.aggregator import collect_data
 from services.sentiment import predict
 from services.evaluation import evaluate_model
+
 from collections import Counter
 import pandas as pd
-from wordcloud import WordCloud
 import os
+import re
+
+from wordcloud import WordCloud
+import matplotlib.pyplot as plt
+import numpy as np
+
+from sklearn.decomposition import LatentDirichletAllocation
+from sklearn.feature_extraction.text import CountVectorizer
+
 
 app = Flask(__name__)
 
-@app.route('/', methods=['GET', 'POST'])
-def index():
-    if request.method == 'POST':
-        keyword = request.form.get('keyword')
-        source = request.form.get('source', 'all')
-
-        data_raw = collect_data(keyword, source)
-
-        texts = [t for s, t in data_raw][:100]
-        sources = [s for s, t in data_raw][:100]
-
-        sentiments = predict(texts)
-
-        counts = Counter(sentiments)
-
-        # 📊 per platform
-        platform_counts = {}
-        for src, sent in zip(sources, sentiments):
-            if src not in platform_counts:
-                platform_counts[src] = {"Positive":0,"Neutral":0,"Negative":0}
-            platform_counts[src][sent] += 1
-
-        # ☁️ wordcloud
-        try:
-            os.makedirs("static", exist_ok=True)
-            wc = WordCloud(width=800, height=400).generate(" ".join(texts))
-            wc.to_file("static/wordcloud.png")
-        except:
-            pass
-
-        # 📁 CSV
-        df = pd.DataFrame({
-            "text": texts,
-            "sentiment": sentiments,
-            "source": sources
-        })
-        df.to_csv("static/result.csv", index=False)
 
-        # 📊 evaluasi
-        eval_result = evaluate_model(predict)
+# =========================
+# 🔥 TOP WORDS
+# =========================
+def get_top_words(texts, top_n=10):
+    words = []
+
+    for t in texts:
+        t = re.sub(r'[^a-zA-Z\s]', '', t.lower())
+        words.extend(t.split())
+
+    common = Counter(words).most_common(top_n)
+    return [{"word": w, "count": c} for w, c in common]
+
+
+# =========================
+# 🔥 HEATMAP
+# =========================
+def generate_heatmap(data):
+    sentiments = [d["sentiment"] for d in data]
+    sources = [d["source"] for d in data]
+
+    labels_sent = ["Positive", "Neutral", "Negative"]
+    labels_src = list(set(sources))
+
+    matrix = np.zeros((len(labels_src), len(labels_sent)))
+
+    for d in data:
+        i = labels_src.index(d["source"])
+        j = labels_sent.index(d["sentiment"])
+        matrix[i][j] += 1
+
+    plt.figure()
+    plt.imshow(matrix)
+
+    plt.xticks(range(len(labels_sent)), labels_sent)
+    plt.yticks(range(len(labels_src)), labels_src)
+
+    for i in range(len(labels_src)):
+        for j in range(len(labels_sent)):
+            plt.text(j, i, int(matrix[i][j]), ha='center')
+
+    plt.title("Heatmap Sentimen")
+    plt.colorbar()
+
+    os.makedirs("static", exist_ok=True)
+    plt.savefig("static/heatmap.png")
+    plt.close()
+
 
-        data = list(zip(texts, sentiments, sources))
+# =========================
+# 🔥 TOPIC MODELING (LDA)
+# =========================
+def get_topics(texts, n_topics=3):
+    vectorizer = CountVectorizer(stop_words='english')
+    X = vectorizer.fit_transform(texts)
 
-        return render_template(
-            "result.html",
-            data=data,
-            counts=counts,
-            platform_counts=platform_counts,
-            eval_result=eval_result,
-            keyword=keyword,
-            source=source
-        )
+    lda = LatentDirichletAllocation(n_components=n_topics, random_state=42)
+    lda.fit(X)
 
+    words = vectorizer.get_feature_names_out()
+
+    topics = []
+    for topic in lda.components_:
+        top_words = [words[i] for i in topic.argsort()[-5:]]
+        topics.append(top_words)
+
+    return topics
+
+
+# =========================
+# 🤖 AI INSIGHT
+# =========================
+def generate_insight(data, topics):
+    sentiments = [d["sentiment"] for d in data]
+    total = len(sentiments)
+
+    pos = sentiments.count("Positive")
+    neg = sentiments.count("Negative")
+    neu = sentiments.count("Neutral")
+
+    insight = f"""
+Total data: {total}
+
+Positive: {pos}
+Negative: {neg}
+Neutral: {neu}
+
+Mayoritas opini adalah {"positif" if pos > neg else "negatif"}.
+
+Topik utama:
+"""
+
+    for i, t in enumerate(topics):
+        insight += f"\nTopik {i+1}: {', '.join(t)}"
+
+    return insight
+
+
+# =========================
+# 🌐 HALAMAN UTAMA
+# =========================
+@app.route('/')
+def home():
     return render_template("index.html")
 
 
+# =========================
+# 🚀 ANALYZE API (AJAX)
+# =========================
+@app.route('/analyze', methods=['POST'])
+def analyze():
+    keyword = request.json.get('keyword')
+    source = request.json.get('source', 'all')
+
+    # ambil data
+    data_raw = collect_data(keyword, source)
+
+    texts = [t for s, t in data_raw][:100]
+    sources = [s for s, t in data_raw][:100]
+
+    sentiments = predict(texts)
+
+    result = []
+    for t, s, src in zip(texts, sentiments, sources):
+        result.append({
+            "text": t,
+            "sentiment": s,
+            "source": src
+        })
+
+    # =====================
+    # 🔥 WORDCLOUD
+    # =====================
+    try:
+        os.makedirs("static", exist_ok=True)
+        wc = WordCloud(width=800, height=400).generate(" ".join(texts))
+        wc.to_file("static/wordcloud.png")
+    except:
+        pass
+
+    # =====================
+    # 📁 CSV EXPORT
+    # =====================
+    df = pd.DataFrame(result)
+    df.to_csv("static/result.csv", index=False)
+
+    # =====================
+    # 📊 HEATMAP
+    # =====================
+    generate_heatmap(result)
+
+    # =====================
+    # 🔥 TOP WORDS
+    # =====================
+    top_words = get_top_words(texts)
+
+    # =====================
+    # 🧠 TOPIC MODELING
+    # =====================
+    topics = get_topics(texts)
+
+    # =====================
+    # 🤖 AI INSIGHT
+    # =====================
+    insight = generate_insight(result, topics)
+
+    # =====================
+    # 📊 EVALUASI MODEL
+    # =====================
+    eval_result = evaluate_model(predict)
+
+    return jsonify({
+        "data": result,
+        "top_words": top_words,
+        "topics": topics,
+        "insight": insight,
+        "eval": eval_result
+    })
+
+
+# =========================
+# 📥 DOWNLOAD CSV
+# =========================
 @app.route('/download')
 def download():
     return send_file("static/result.csv", as_attachment=True)
 
 
+# =========================
+# ▶️ RUN
+# =========================
 if __name__ == "__main__":
     app.run(host="0.0.0.0", port=7860)