feat: initial release of network analyzer space

README.md

@@ -0,0 +1,19 @@
+---
+title: Co-occurrence Networks
+emoji: 📊
+colorFrom: red
+colorTo: orange
+sdk: gradio
+app_file: app.py
+pinned: false
+---
+
+# Word Co-occurrence Networks
+
+An interactive computational linguistics application that maps and visualizes word co-occurrences based on textual proximity. Useful for analyzing key themes, concept maps, and stylistic structures in literature, media, and digital archives.
+
+### Features
+1. **Interactive Visualizations**: Zoom, drag, and toggle physics-enabled word-word network visualizations using Vis.js.
+2. **Custom Stopwords**: Filter out noise words and focus on high-value conceptual connections.
+3. **Sliding Window Adjustment**: Control how far apart two words can be (window size) to construct a connection.
+4. **Data Exports**: Download a clean, sorted edge list CSV for further network analysis in tools like Gephi.

app.py

@@ -0,0 +1,267 @@
+import gradio as gr
+import pandas as pd
+import networkx as nx
+from pyvis.network import Network
+import tempfile
+import os
+import re
+from collections import Counter
+
+# A robust built-in stopword list to guarantee functionality even without downloading NLTK datasets
+DEFAULT_STOPWORDS = set([
+    "i", "me", "my", "myself", "we", "our", "ours", "ourselves", "you", "your", "yours", 
+    "yourself", "yourselves", "he", "him", "his", "himself", "she", "her", "hers", 
+    "herself", "it", "its", "itself", "they", "them", "their", "theirs", "themselves", 
+    "what", "which", "who", "whom", "this", "that", "these", "those", "am", "is", "are", 
+    "was", "were", "be", "been", "being", "have", "has", "had", "having", "do", "does", 
+    "did", "doing", "a", "an", "the", "and", "but", "if", "or", "because", "as", "until", 
+    "while", "of", "at", "by", "for", "with", "about", "against", "between", "into", 
+    "through", "during", "before", "after", "above", "below", "to", "from", "up", "down", 
+    "in", "out", "on", "off", "over", "under", "again", "further", "then", "once", "here", 
+    "there", "when", "where", "why", "how", "all", "any", "both", "each", "few", "more", 
+    "most", "other", "some", "such", "no", "nor", "not", "only", "own", "same", "so", 
+    "than", "too", "very", "s", "t", "can", "will", "just", "don", "should", "now", "d", 
+    "ll", "m", "o", "re", "ve", "y", "ain", "aren", "couldn", "didn", "doesn", "hadn", 
+    "hasn", "haven", "isn", "ma", "mightn", "mustn", "needn", "shan", "shouldn", "wasn", 
+    "weren", "won", "wouldn"
+])
+
+def tokenize_and_clean(text, custom_stopwords_str):
+    # Convert custom stopwords
+    custom_stops = set([w.strip().lower() for w in custom_stopwords_str.split(',') if w.strip()])
+    all_stopwords = DEFAULT_STOPWORDS.union(custom_stops)
+    
+    # Simple regex tokenizer
+    words = re.findall(r'\b[a-zA-Z]{2,}\b', text.lower())
+    cleaned_words = [w for w in words if w not in all_stopwords]
+    return cleaned_words
+
+def build_cooccurrence_matrix(words, window_size):
+    cooccurrences = Counter()
+    
+    for i in range(len(words)):
+        current_word = words[i]
+        # Look ahead up to the window size
+        start = i + 1
+        end = min(i + 1 + window_size, len(words))
+        
+        for j in range(start, end):
+            next_word = words[j]
+            if current_word != next_word:
+                # Sort alphabetically to keep edges undirected
+                pair = tuple(sorted([current_word, next_word]))
+                cooccurrences[pair] += 1
+                
+    return cooccurrences
+
+def generate_vis_html(cooccurrences, min_freq, word_counts):
+    # Filter by minimum frequency
+    filtered_pairs = {pair: count for pair, count in cooccurrences.items() if count >= min_freq}
+    
+    if not filtered_pairs:
+        return None, None
+        
+    # Extract unique nodes from filtered edges
+    nodes = set()
+    for pair in filtered_pairs.keys():
+        nodes.update(pair)
+        
+    # Initialize PyVis Network
+    net = Network(
+        height="500px", 
+        width="100%", 
+        bgcolor="#16100c", 
+        font_color="#f4eee6", 
+        notebook=False
+    )
+    
+    net.set_options("""
+    var options = {
+      "nodes": {
+        "borderWidth": 1,
+        "borderWidthSelected": 3,
+        "color": {
+          "border": "#2c1e16",
+          "background": "#ff7043",
+          "highlight": {
+            "border": "#ff7043",
+            "background": "#ffffff"
+          }
+        },
+        "font": {
+          "color": "#f4eee6",
+          "size": 14,
+          "face": "Inter, sans-serif"
+        }
+      },
+      "edges": {
+        "color": {
+          "color": "rgba(255, 112, 67, 0.3)",
+          "highlight": "#ff7043"
+        },
+        "smooth": {
+          "type": "continuous"
+        }
+      },
+      "physics": {
+        "barnesHut": {
+          "gravitationalConstant": -15000,
+          "centralGravity": 0.35,
+          "springLength": 100,
+          "springConstant": 0.05
+        },
+        "minVelocity": 0.75
+      }
+    }
+    """)
+    
+    # Add nodes (scaled by absolute frequency in the text)
+    for node in nodes:
+        freq = word_counts.get(node, 1)
+        size = 10 + min(freq * 1.5, 40)  # Caps size to prevent massive nodes
+        net.add_node(node, label=node, size=size, title=f"Word occurrences: {freq}")
+        
+    # Add edges
+    for (source, target), weight in filtered_pairs.items():
+        net.add_edge(source, target, value=weight, title=f"Co-occurrences: {weight}")
+        
+    # Save graph and read
+    temp_dir = tempfile.gettempdir()
+    temp_path = os.path.join(temp_dir, next(tempfile._get_candidate_names()) + ".html")
+    net.save_graph(temp_path)
+    
+    with open(temp_path, "r", encoding="utf-8") as f:
+        html_content = f.read()
+        
+    try:
+        os.remove(temp_path)
+    except:
+        pass
+        
+    escaped_html = html_content.replace('"', '"')
+    iframe_code = f'<iframe srcdoc="{escaped_html}" style="width: 100%; height: 530px; border: 1px solid rgba(255, 255, 255, 0.08); border-radius: 8px;"></iframe>'
+    
+    # Create DataFrame for display/download
+    edge_list = [{"Source": k[0], "Target": k[1], "Co-occurrences": v} for k, v in filtered_pairs.items()]
+    df = pd.DataFrame(edge_list).sort_values("Co-occurrences", ascending=False)
+    
+    return iframe_code, df
+
+def analyze_cooccurrence(text, window_size, min_freq, custom_stopwords):
+    if not text or len(text.strip()) < 10:
+        return "Please input a longer block of text.", None, None, None
+        
+    words = tokenize_and_clean(text, custom_stopwords)
+    if len(words) < 5:
+        return "Not enough meaningful words found after filtering stopwords.", None, None, None
+        
+    word_counts = Counter(words)
+    cooccurrences = build_cooccurrence_matrix(words, window_size)
+    
+    vis_html, df = generate_vis_html(cooccurrences, min_freq, word_counts)
+    
+    if vis_html is None:
+        return f"No word pairs met the minimum co-occurrence threshold of {min_freq}. Try lowering the slider.", None, None, None
+        
+    # Stats
+    num_nodes = len(df['Source'].unique()) + len(df['Target'].unique())
+    num_edges = len(df)
+    
+    stats_html = f"""
+    <div style='display: grid; grid-template-columns: repeat(2, 1fr); gap: 1rem; margin-bottom: 1rem;'>
+        <div style='background: rgba(255, 255, 255, 0.03); border: 1px solid rgba(255, 255, 255, 0.08); border-radius: 8px; padding: 1rem; text-align: center;'>
+            <div style='font-size: 0.75rem; text-transform: uppercase; color: #ff7043; letter-spacing: 0.1em;'>Words in Network</div>
+            <div style='font-size: 2rem; font-weight: bold; margin-top: 0.5rem;'>{num_nodes}</div>
+        </div>
+        <div style='background: rgba(255, 255, 255, 0.03); border: 1px solid rgba(255, 255, 255, 0.08); border-radius: 8px; padding: 1rem; text-align: center;'>
+            <div style='font-size: 0.75rem; text-transform: uppercase; color: #ff7043; letter-spacing: 0.1em;'>Unique Word Pairs (Links)</div>
+            <div style='font-size: 2rem; font-weight: bold; margin-top: 0.5rem;'>{num_edges}</div>
+        </div>
+    </div>
+    """
+    
+    # Download file path
+    out_csv = tempfile.mktemp(suffix=".csv")
+    df.to_csv(out_csv, index=False)
+    
+    return "", stats_html, vis_html, df.head(50), out_csv
+
+theme = gr.themes.Default(
+    primary_hue="orange",
+    neutral_hue="stone"
+).set(
+    body_background_fill="#0d0907",
+    body_text_color="#c4bbae",
+    block_background_fill="#16100c",
+    block_border_width="1px",
+    block_label_text_color="#f4eee6"
+)
+
+with gr.Blocks(theme=theme, title="Word Co-occurrence Networks") as demo:
+    gr.Markdown(
+        """
+        # 📊 Interactive Word Co-occurrence Networks
+        ### Map how words and concepts interconnect based on proximity. Perfect for structural linguistics, narrative themes, and semantic modeling.
+        """
+    )
+    
+    error_msg = gr.Markdown("", visible=False)
+    
+    with gr.Row():
+        with gr.Column(scale=1):
+            raw_text = gr.Textbox(
+                label="Input Text Document", 
+                placeholder="Paste your textual content here (e.g. speeches, novel chapters, or code blocks)...", 
+                lines=10
+            )
+            
+            with gr.Row():
+                window_size = gr.Slider(
+                    minimum=2, 
+                    maximum=10, 
+                    value=5, 
+                    step=1, 
+                    label="Sliding Window Size",
+                    info="Maximum distance in words to capture a connection."
+                )
+                min_freq = gr.Slider(
+                    minimum=1, 
+                    maximum=20, 
+                    value=3, 
+                    step=1, 
+                    label="Min Co-occurrence Frequency",
+                    info="Filters out peripheral connections."
+                )
+                
+            custom_stopwords = gr.Textbox(
+                label="Custom Stopwords (comma separated)",
+                placeholder="chapter, page, said, would",
+                info="Words to ignore during co-occurrence analysis."
+            )
+            
+            btn = gr.Button("Build Co-occurrence Network", variant="primary")
+            
+        with gr.Column(scale=2):
+            stats_box = gr.HTML()
+            
+            with gr.Tabs():
+                with gr.TabItem("Interactive Graph"):
+                    vis_box = gr.HTML()
+                with gr.TabItem("Data Table"):
+                    table_box = gr.Dataframe(headers=["Source", "Target", "Co-occurrences"])
+                    download_btn = gr.File(label="Download Full Dataset")
+
+    def process(text, window, freq, stops):
+        err, stats, vis, table, csv_path = analyze_cooccurrence(text, window, freq, stops)
+        if err:
+            return gr.update(value=err, visible=True), "", "", None, gr.update(visible=False)
+        return gr.update(visible=False), stats, vis, table, gr.update(value=csv_path, visible=True)
+
+    btn.click(
+        process,
+        inputs=[raw_text, window_size, min_freq, custom_stopwords],
+        outputs=[error_msg, stats_box, vis_box, table_box, download_btn]
+    )
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,3 @@
+pandas
+networkx
+pyvis