File size: 5,212 Bytes
256b89c
64657d1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
256b89c
64657d1
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
import streamlit as st
import pandas as pd
import numpy as np
import joblib
import matplotlib.pyplot as plt
from sklearn.decomposition import PCA

st.set_page_config(page_title="KMeans User Segmentation", layout="centered")

st.title("πŸ‘₯ KMeans User Segmentation")
st.write("Upload a CSV or enter values manually to assign users into **KMeans clusters**.")

# -----------------------------
# Load artifacts
# -----------------------------
@st.cache_resource
def load_artifacts():
    model = joblib.load("src/kmeans_user_segmentation.pkl")
    scaler = joblib.load("src/scaler.pkl")
    return model, scaler

model, scaler = load_artifacts()
st.success("Model + scaler loaded successfully βœ…")

# -----------------------------
# Feature columns used in training
# -----------------------------
FEATURES = [
    "Average Screen Time",
    "Average Spent on App (INR)",
    "Ratings",
    "Last Visited Minutes",
    "New Password Request",
]

# -----------------------------
# Sidebar options
# -----------------------------
st.sidebar.header("βš™οΈ Options")
input_mode = st.sidebar.radio("Input method", ["Upload CSV", "Manual Input"])
show_pca = st.sidebar.checkbox("Show PCA 2D plot (based on input data)", value=True)

# -----------------------------
# Helper: validate + prepare
# -----------------------------
def prepare_features(df: pd.DataFrame) -> pd.DataFrame:
    missing = [c for c in FEATURES if c not in df.columns]
    if missing:
        raise ValueError(f"Missing columns: {missing}")
    X = df[FEATURES].copy()
    # Make sure numeric
    for c in FEATURES:
        X[c] = pd.to_numeric(X[c], errors="coerce")
    if X.isna().any().any():
        bad_cols = X.columns[X.isna().any()].tolist()
        raise ValueError(f"Non-numeric or missing values found in: {bad_cols}. Please clean your CSV.")
    return X

# -----------------------------
# Input: CSV
# -----------------------------
df = None

if input_mode == "Upload CSV":
    uploaded = st.file_uploader("Upload CSV", type=["csv"])
    if uploaded is None:
        st.info("Upload a CSV to start.")
    else:
        df = pd.read_csv(uploaded)
        st.subheader("πŸ“„ Data Preview")
        st.dataframe(df.head())

# -----------------------------
# Input: Manual
# -----------------------------
else:
    st.info("Manual input is best for quick testing. For real segmentation, use CSV upload.")
    n = st.slider("Number of users (rows)", 1, 20, 5)

    rows = []
    for i in range(n):
        st.markdown(f"### User {i+1}")
        c1, c2 = st.columns(2)
        screen_time = c1.number_input("Average Screen Time", min_value=0.0, value=10.0, key=f"st_{i}")
        spent = c2.number_input("Average Spent on App (INR)", min_value=0.0, value=100.0, key=f"sp_{i}")

        c3, c4 = st.columns(2)
        ratings = c3.number_input("Ratings", min_value=0.0, value=7.0, key=f"ra_{i}")
        last_visit = c4.number_input("Last Visited Minutes", min_value=0.0, value=1000.0, key=f"lv_{i}")

        pwd_req = st.number_input("New Password Request", min_value=0.0, value=1.0, key=f"pw_{i}")

        rows.append([screen_time, spent, ratings, last_visit, pwd_req])

    df = pd.DataFrame(rows, columns=FEATURES)
    st.subheader("πŸ“„ Manual Data")
    st.dataframe(df)

# -----------------------------
# Predict
# -----------------------------
if df is not None and len(df) > 0:
    try:
        X = prepare_features(df)
        X_scaled = scaler.transform(X)

        clusters = model.predict(X_scaled)
        out = df.copy()
        out["cluster"] = clusters

        st.subheader("βœ… Cluster Results")
        st.dataframe(out.head(20))

        st.subheader("πŸ“Š Cluster Distribution")
        st.write(out["cluster"].value_counts().sort_index())

        # Cluster profile (means)
        st.subheader("πŸ“Œ Cluster Profile (mean values)")
        profile = out.groupby("cluster")[FEATURES].mean(numeric_only=True).round(2)
        st.dataframe(profile)

        # Simple bar chart for profile
        st.subheader("πŸ“ˆ Average Feature Values per Cluster")
        fig, ax = plt.subplots(figsize=(9, 4))
        profile.plot(kind="bar", ax=ax)
        ax.set_xlabel("Cluster")
        ax.set_ylabel("Mean value")
        ax.legend(loc="best")
        st.pyplot(fig)

        # PCA plot (optional)
        if show_pca and len(out) >= 3:
            pca = PCA(n_components=2, random_state=42)
            X_pca = pca.fit_transform(X_scaled)

            st.subheader("🧭 PCA 2D Projection (Input Data)")
            fig2, ax2 = plt.subplots(figsize=(6, 5))
            sc = ax2.scatter(X_pca[:, 0], X_pca[:, 1], c=clusters)
            ax2.set_title("KMeans Clusters (PCA Projection)")
            ax2.set_xlabel("PC1")
            ax2.set_ylabel("PC2")
            st.pyplot(fig2)

        # Download results
        st.subheader("⬇️ Download")
        csv = out.to_csv(index=False).encode("utf-8")
        st.download_button("Download results CSV", csv, file_name="clustered_users.csv", mime="text/csv")

        st.info("Tip: Clustering is unsupervised β€” clusters are groups with similar behavior patterns, not 'correct/incorrect' labels.")

    except Exception as e:
        st.error(str(e))
        st.stop()