Update app.py

app.py

@@ -1,77 +1,3 @@
-
-# ------------------------------------------------------------
-# NEW — Dimensional‑reduction / clustering feature
-# ------------------------------------------------------------
-def dim_reduction(method='t-SNE', perplexity=30, n_neighbors=15, min_dist=0.1,
-                  use_cnn=False, cluster_eps=0.5, cluster_min_samples=5):
-    """
-    Compute 2‑D embedding (t‑SNE or UMAP) of per‑storm features.
-    Returns a Plotly Figure and an info string.
-    """
-    global typhoon_max, typhoon_data
-    if typhoon_max is None:
-        return None, "No typhoon data loaded."
-
-    df = typhoon_max.copy()
-
-    # Select features
-    if use_cnn and TF_AVAILABLE:
-        MAX_LEN = 100
-        grouped = typhoon_data.groupby('SID')
-        sequences = []
-        for sid in df['SID']:
-            winds = grouped.get_group(sid)['USA_WIND'].fillna(0).values if sid in grouped.groups else []
-            winds = winds[:MAX_LEN]
-            seq = np.zeros(MAX_LEN, dtype=np.float32)
-            seq[:len(winds)] = winds
-            sequences.append(seq)
-        X = np.stack(sequences)[..., None]
-
-        model = models.Sequential([
-            layers.Conv1D(16, 5, activation='relu', input_shape=(MAX_LEN,1)),
-            layers.MaxPool1D(2),
-            layers.Conv1D(32, 3, activation='relu'),
-            layers.GlobalAveragePooling1D(),
-            layers.Dense(32, activation='relu')
-        ])
-        embeddings = model.predict(X, verbose=0)
-        features_for_dr = embeddings
-        feature_text = "CNN latent vectors"
-    else:
-        features = ['USA_WIND','USA_PRES','LAT','LON']
-        features_for_dr = df[features].fillna(0).values
-        feature_text = ", ".join(features)
-
-    from sklearn.preprocessing import StandardScaler
-    X_std = StandardScaler().fit_transform(features_for_dr)
-
-    if method == 't-SNE':
-        from sklearn.manifold import TSNE
-        reducer = TSNE(n_components=2, init='pca', perplexity=perplexity, learning_rate='auto', random_state=0)
-        coords = reducer.fit_transform(X_std)
-    else:
-        reducer = umap.UMAP(n_neighbors=n_neighbors, min_dist=min_dist, n_components=2, random_state=0)
-        coords = reducer.fit_transform(X_std)
-
-    df['DR_X'] = coords[:,0]
-    df['DR_Y'] = coords[:,1]
-
-    from sklearn.cluster import DBSCAN
-    clusterer = DBSCAN(eps=cluster_eps, min_samples=cluster_min_samples)
-    labels = clusterer.fit_predict(coords)
-    df['Cluster'] = labels.astype(str)
-
-    import plotly.express as px
-    fig = px.scatter(
-        df, x='DR_X', y='DR_Y',
-        color='Category', symbol='Cluster',
-        hover_data={'Name': df['NAME'], 'Year': df['Year'], 'Wind': df['USA_WIND'], 'Pressure': df['USA_PRES']},
-        title=f"{method} embedding (features: {feature_text})"
-    )
-    fig.update_traces(marker=dict(size=6, line=dict(width=0.5,color='black')))
-    info=f"Method: {method} | Points: {len(df)} | Clusters: {len(set(labels))-('-1' in set(labels))}"
-    return fig, info
-
 import os
 import argparse
 import logging
@@ -84,13 +10,6 @@ import csv
 import gradio as gr
 import pandas as pd
 import numpy as np
-import umap   # NEW
-try:
-    import tensorflow as tf
-    from tensorflow.keras import layers, models
-    TF_AVAILABLE = True
-except Exception:
-    TF_AVAILABLE = False
 import matplotlib.pyplot as plt
 import matplotlib.animation as animation
 from matplotlib.backends.backend_agg import FigureCanvasAgg as FigureCanvas
@@ -1243,27 +1162,6 @@ def create_interface():
                     outputs=[regression_plot, slopes_text, lon_regression_results]
                 )
             
-            
-# ---- Dimensional Reduction (t‑SNE / UMAP) ----
-with gr.Tab("Dimensional Reduction (t‑SNE / UMAP)"):
-    dr_method   = gr.Dropdown(['t-SNE','UMAP'], label="Method", value='t-SNE')
-    tsne_perp   = gr.Slider(5,100,step=5,value=30,label="t‑SNE Perplexity")
-    umap_nn     = gr.Slider(5,100,step=1,value=15,label="UMAP n_neighbors")
-    umap_md     = gr.Slider(0.0,1.0,step=0.05,value=0.1,label="UMAP min_dist")
-    use_cnn_box = gr.Checkbox(label="Use CNN latent features", value=False, visible=TF_AVAILABLE)
-    cluster_eps = gr.Slider(0.1,5.0,step=0.1,value=0.5,label="DBSCAN ε")
-    cluster_min = gr.Slider(2,20,step=1,value=5,label="DBSCAN min_samples")
-    dr_btn      = gr.Button("Compute Embedding")
-    dr_plot     = gr.Plot()
-    dr_info     = gr.Textbox(label="Info")
-    def _dr_wrapper(method, perp, nn, md, cnn, eps, mns):
-        return dim_reduction(method, perp, nn, md, cnn, eps, mns)
-    dr_btn.click(
-        fn=_dr_wrapper,
-        inputs=[dr_method, tsne_perp, umap_nn, umap_md, use_cnn_box, cluster_eps, cluster_min],
-        outputs=[dr_plot, dr_info]
-    )
-
             with gr.Tab("Tropical Cyclone Path Animation"):
                 with gr.Row():
                     year_dropdown = gr.Dropdown(label="Year", choices=[str(y) for y in range(1950, 2025)], value="2000")