Update W3-assignment-streamlit.py

W3-assignment-streamlit.py

@@ -6,6 +6,7 @@ import pandas as pd
 import numpy as np
 import matplotlib.pyplot as plt
 
+
 from sklearn.impute import SimpleImputer
 from sklearn.preprocessing import StandardScaler
 from sklearn.decomposition import PCA
@@ -21,21 +22,28 @@ st.sidebar.title("Controls")
 import os
 from pathlib import Path
 
-candidates = [
-    "youtube_shorts_tiktok_trends_2025.csv",         
-    "data/youtube_shorts_tiktok_trends_2025.csv"     
-]
-
-CSV_PATH = None
-for p in candidates:
-    if Path(p).exists():
-        CSV_PATH = p
-        break
+@st.cache_data(show_spinner=False)
+def load_data() -> pd.DataFrame:
+    """
+    Try both locations:
+    1) data/youtube_shorts_tiktok_trends_2025.csv
+    2) ./youtube_shorts_tiktok_trends_2025.csv
+    """
+    candidates = [
+        Path("data/youtube_shorts_tiktok_trends_2025.csv"),
+        Path("youtube_shorts_tiktok_trends_2025.csv"),
+    ]
+    for p in candidates:
+        if p.exists():
+            return pd.read_csv(p, low_memory=False)
 
-assert CSV_PATH is not None, f"CSV not found in: {candidates}"
+    raise FileNotFoundError(
+        f"CSV not found in any of: {[str(p) for p in candidates]}. "
+        "Make sure the file is committed to your Space."
+    )
 
-# Load dataset
-df_raw = pd.read_csv(CSV_PATH, low_memory=False)
+# load data
+df_raw = load_data()
 
 # Choose number of clusters (K)
 k = st.sidebar.slider("Number of clusters (K)", min_value=2, max_value=8, value=4, step=1)