Spaces:
Sleeping
Sleeping
File size: 2,927 Bytes
bb52310 001d24f bb52310 | 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 | import streamlit as st
import numpy as np
import matplotlib.pyplot as plt
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import accuracy_score,f1_score
from sklearn.model_selection import train_test_split
from sklearn.datasets import make_classification, make_circles, make_blobs, make_moons
from mlxtend.plotting import plot_decision_regions, plot_learning_curves
# Streamlit UI
st.set_page_config(page_title="KNN Classifier App", layout="wide")
st.title("🔍 KNN Classifier Interactive App")
st.write("Select a dataset, modify parameters, and tune KNN hyperparameters.")
# Sidebar options
dataset_choice = st.sidebar.selectbox("📂 Select a Dataset", ["Classification", "Circles", "Blobs", "Moons"])
# Dataset parameters
if dataset_choice == "Classification":
n_samples = st.sidebar.slider("Samples", 1000, 5000, 2000)
class_sep = st.sidebar.slider("Class Separation", 0.5, 5.0, 1.0)
X, y = make_classification(n_samples=n_samples, n_features=2, n_redundant=0,
n_clusters_per_class=1, class_sep=class_sep, random_state=23)
elif dataset_choice == "Circles":
n_samples = st.sidebar.slider("Samples", 500, 5000, 2000)
noise = st.sidebar.slider("Noise", 0.0, 0.5, 0.2)
factor = st.sidebar.slider("Factor", 0.1, 0.9, 0.2)
X, y = make_circles(n_samples=n_samples, factor=factor, noise=noise, random_state=23)
elif dataset_choice == "Blobs":
n_samples = st.sidebar.slider("Samples", 500, 5000, 2000)
clusters = st.sidebar.slider("Clusters", 2, 5, 3)
X, y = make_blobs(n_samples=n_samples, centers=clusters, n_features=2, random_state=23)
else: # Moons
n_samples = st.sidebar.slider("Samples", 500, 5000, 2000)
noise = st.sidebar.slider("Noise", 0.0, 0.5, 0.2)
X, y = make_moons(n_samples=n_samples, noise=noise, random_state=23)
# Split dataset
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=23)
# KNN Parameters
st.sidebar.subheader("⚙️ KNN Parameters")
n_neighbors = st.sidebar.slider("Neighbors (k)", 1, 15, 3)
weights = st.sidebar.selectbox("Weights", ["uniform", "distance"])
p = st.sidebar.selectbox("p (Minkowski)", [1, 2])
# Train KNN
knn = KNeighborsClassifier(n_neighbors=n_neighbors, weights=weights, p=p, metric='minkowski')
knn.fit(X_train, y_train)
y_pred = knn.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
f1=f1_score(y_test,y_pred,average="weighted")
# Display results
st.subheader("📊 Model Accuracy")
st.write(f"**Accuracy Score: {accuracy:.4f}**")
st.subheader("📊 Model F1-Score")
st.write(f"**F1 Score: {f1:.4f}**")
fig, ax = plt.subplots(figsize=(6, 4))
plot_learning_curves(X_train, y_train, X_test, y_test, knn, scoring='accuracy')
st.subheader("📈 Learning Curve")
st.pyplot(fig)
fig, ax = plt.subplots(figsize=(6, 4))
knn.fit(X, y)
plot_decision_regions(X, y, knn)
st.subheader("🔷 Decision Boundary")
st.pyplot(fig)
|