Upload 4 files

app.py

@@ -0,0 +1,77 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+from sklearn.neighbors import NearestNeighbors
+
+# Load data
+df = pd.read_csv("cities.csv")
+df_preprocessed = np.loadtxt("df_processed.csv", delimiter=',') # exported after preprocessing step in lecture example
+
+st.title("🌍 City Similarity Recommender")
+
+# City selection
+selected_places = st.multiselect("Select one or more cities you like:", options=df['place'].tolist())
+
+# Optional sub-region filter
+subregion_options = ['All'] + sorted(df['sub-region'].unique().tolist())
+selected_subregion = st.selectbox("Optionally filter recommended city by sub-region:", options=subregion_options)
+
+if selected_places:
+    # Get indices of selected cities
+    selected_indices = df[df['place'].isin(selected_places)].index.tolist()
+
+    # Compute the average feature vector
+    avg_vector = df_preprocessed[selected_indices].mean(axis=0).reshape(1, -1)
+
+    # Apply sub-region filtering if selected
+    if selected_subregion != 'All':
+        candidate_mask = (df['sub-region'] == selected_subregion)
+        candidate_mask[selected_indices] = False
+    else:
+        candidate_mask = np.ones(len(df), dtype=bool)
+        candidate_mask[selected_indices] = False
+
+    candidate_indices = np.where(candidate_mask)[0]
+    candidate_vectors = df_preprocessed[candidate_indices]
+
+    # Use NearestNeighbors to find top 3 closest
+    nn = NearestNeighbors(n_neighbors=3, metric='euclidean')
+    nn.fit(candidate_vectors)
+    distances, indices = nn.kneighbors(avg_vector)
+
+    top_indices = [candidate_indices[i] for i in indices[0]]
+
+    st.subheader("🔍 Top 3 Similar Cities")
+    for rank, idx in enumerate(top_indices, 1):
+        city = df.iloc[idx]
+        st.markdown(f"### {rank}. {city['place']}")
+        st.markdown(f"Country: {city['alpha-2']}")
+        st.markdown(f"Region: {city['region']}")
+        st.markdown(f"Sub-region: {city['sub-region']}")
+        st.markdown(f"Similarity score (Euclidean distance): {round(distances[0][rank - 1], 4)}")
+        st.markdown("---")
+else:
+    st.info("Please select at least one city to get a recommendation.")
+
+# --- Explanatory Sections ---
+
+with st.expander("🧠 Technique Used"):
+    st.markdown("""
+    This recommender uses **unsupervised learning techniques** to find the most similar cities based on selected examples. Here's how it works:
+
+    - The app uses **scaled numerical features** that describe cities in terms of cost, safety, infrastructure, and lifestyle.
+    - When you select cities you like, their feature vectors are averaged.
+    - We then use **k-Nearest Neighbors (k-NN)** to find the top 3 most similar cities based on **Euclidean distance**.
+    - Optionally, results can be limited to a **specific sub-region**.
+    """)
+
+with st.expander("📚 Why this is Unsupervised Learning"):
+    st.markdown("""
+    This approach is a classic example of **unsupervised learning (UML)**:
+
+    - There are **no labels or targets** provided — we don’t tell the model what to predict.
+    - Instead, we explore the **structure of the data** to find **similarities** and groupings.
+    - The recommendation is based purely on feature-based proximity — no training labels are used.
+
+    Techniques like clustering and similarity search (like k-NN) are key tools in the UML toolbox — making this system a real-life application of UML.
+    """)

requirements.txt

@@ -0,0 +1,4 @@
+streamlit
+pandas
+numpy
+scikit-learn