Upload 3 files

app.py

@@ -0,0 +1,66 @@
+import streamlit as st
+import pandas as pd
+import matplotlib.pyplot as plt
+from datasets import load_dataset
+from sklearn.preprocessing import StandardScaler
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.preprocessing import LabelEncoder
+
+st.title("🌸 AI Flower Species Classification System")
+st.write("Built with **K-Nearest Neighbors (KNN)** and trained using a dataset fetched live from **Hugging Face**.")
+
+@st.cache_data
+def load_hf_data():
+    dataset = load_dataset("scikit-learn/iris", split="train")
+    return pd.DataFrame(dataset)
+
+with st.spinner("Fetching dataset from Hugging Face..."):
+    df = load_hf_data()
+
+st.success("Dataset successfully loaded from Hugging Face!")
+
+# Dynamically select features and target
+feature_columns = df.columns[:4]
+target_column = df.columns[-1]
+
+X = df[feature_columns]
+y_text = df[target_column]
+
+# Convert text labels (Iris-setosa, etc.) into numbers (0, 1, 2) for model and graph coloring
+encoder = LabelEncoder()
+y = encoder.fit_transform(y_text)
+
+# Scale and Train KNN Model
+scaler = StandardScaler()
+X_scaled = scaler.fit_transform(X)
+
+knn = KNeighborsClassifier(n_neighbors=3)
+knn.fit(X_scaled, y)
+
+# Sidebar UI Controls for User Input
+st.sidebar.header("🎛️ Input Flower Measurements")
+inputs = []
+for col in feature_columns:
+    val = st.sidebar.slider(f"{col}", float(X[col].min()), float(X[col].max()), float(X[col].mean()))
+    inputs.append(val)
+
+# Prediction Button
+if st.button("Predict Species"):
+    user_input = scaler.transform([inputs])
+    pred = knn.predict(user_input)
+    
+    predicted_name = encoder.inverse_transform(pred)[0]
+    
+    st.subheader("✨ Result:")
+    st.success(f"The predicted flower species is: **{predicted_name}**")
+
+# Graph Visualization
+st.subheader("📊 Dataset Visualization & Your Input")
+fig, ax = plt.subplots(figsize=(8, 5))
+scatter = ax.scatter(X.iloc[:, 0], X.iloc[:, 1], c=y, cmap='viridis', s=60, edgecolors='k', label='Dataset Clusters')
+ax.scatter(inputs[0], inputs[1], color='red', marker='X', s=250, label='Your Custom Input')
+ax.set_xlabel(feature_columns[0])
+ax.set_ylabel(feature_columns[1])
+plt.colorbar(scatter, label='Species Code')
+ax.legend()
+st.pyplot(fig)

hf_knn_project.py

@@ -0,0 +1,50 @@
+from datasets import load_dataset
+import pandas as pd
+import matplotlib.pyplot as plt
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.metrics import accuracy_score
+
+print("1. Downloading dataset from Hugging Face...")
+# Fetching a clean tabular dataset directly from Hugging Face Hub
+dataset = load_dataset("scikit-learn/iris", split="train")
+df = pd.DataFrame(dataset)
+
+# Features (Measurements) and Target (Species)
+X = df[['sepal length (cm)', 'sepal width (cm)', 'petal length (cm)', 'petal width (cm)']]
+y = df['target']
+
+print("2. Splitting and scaling data...")
+# Split into training and testing sets
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+# Scale features for accurate KNN distance calculations
+scaler = StandardScaler()
+X_train_scaled = scaler.fit_transform(X_train)
+X_test_scaled = scaler.transform(X_test)
+
+print("3. Training the KNN Model...")
+# Train KNN with 3 neighbors
+knn = KNeighborsClassifier(n_neighbors=3)
+knn.fit(X_train_scaled, y_train)
+
+# Check model accuracy
+y_pred = knn.predict(X_test_scaled)
+print(f"Model Accuracy: {accuracy_score(y_test, y_pred) * 100:.2f}%")
+
+# Test a brand new sample prediction
+new_sample = [[5.1, 3.5, 1.4, 0.2]]
+new_sample_scaled = scaler.transform(new_sample)
+prediction = knn.predict(new_sample_scaled)
+print(f"Prediction for new sample [Class]: {prediction[0]}")
+
+print("4. Generating Graph...")
+# Simple 2D plot using first two features (Sepal Length vs Sepal Width)
+plt.figure(figsize=(8, 6))
+plt.scatter(df['sepal length (cm)'], df['sepal width (cm)'], c=df['target'], cmap='viridis', s=80, edgecolors='k')
+plt.title("Hugging Face Dataset - KNN Classification (Iris Sepal Dimensions)")
+plt.xlabel("Sepal Length (cm)")
+plt.ylabel("Sepal Width (cm)")
+plt.grid(True)
+plt.show()

requirements.txt

@@ -0,0 +1,5 @@
+streamlit
+pandas
+matplotlib
+scikit-learn
+datasets