Added files

.gitignore

@@ -0,0 +1 @@
+.venv/

FIFA_Standardized_Data.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1e5a81d1da3e7e335ef9238fb3e7258e29f1523d1c9b017abd681e690be5aa6
+size 2332218

app.py

@@ -0,0 +1,88 @@
+import streamlit as st
+import joblib
+import pandas as pd
+import os
+import matplotlib.pyplot as plt
+import seaborn as sns
+from sklearn.decomposition import PCA
+from datasets import load_dataset
+
+def load_clustered_data():
+    df = joblib.load("FIFA_Standardized_Data.joblib")
+    
+    # Ensure required clustering columns exist
+    required_columns = ["DBSCAN_Cluster", "PCA1", "PCA2", "TSNE1", "TSNE2"]
+    missing_columns = [col for col in required_columns if col not in df.columns]
+    
+    if missing_columns:
+        st.error(f"⚠️ Missing columns in dataset: {', '.join(missing_columns)}. Please re-run clustering and save the dataset.")
+        return None
+    
+    return df
+
+def load_fifa_dataset():
+    dataset = load_dataset("Ci-Dave/FIFA2019")
+    df = pd.DataFrame(dataset["train"])
+    df.rename(columns={"ShortPassing": "Passing", "StandingTackle": "Defending", "Strength": "Physical"}, inplace=True)
+    return df
+
+def home_page():
+    st.title("⚽ FIFA 2019 Clustering Analysis")
+    st.write("""
+    This Streamlit app demonstrates unsupervised learning using **clustering techniques** on the FIFA 2019 dataset.
+    
+    **Key Features:**
+    - Displays the dataset
+    - Allows user interaction for visualizing clusters
+    - Uses models like **DBSCAN, PCA, and t-SNE**
+    """)
+
+def dataset_page():
+    st.title("📊 FIFA 2019 Dataset")
+    df = load_fifa_dataset()
+    st.dataframe(df)
+
+def visualization_page():
+    st.title("📈 Clustering Visualization")
+    df = load_clustered_data()
+    
+    if df is None:
+        return  # Stop execution if dataset is missing required columns
+    
+    clustering_algorithms = ["DBSCAN", "PCA", "t-SNE"]
+    selected_algo = st.selectbox("Choose a Clustering Algorithm:", clustering_algorithms)
+    
+    if selected_algo == "DBSCAN":
+        st.subheader("DBSCAN Clustering")
+        plt.figure(figsize=(8,5))
+        sns.scatterplot(x=df["PCA1"], y=df["PCA2"], hue=df["DBSCAN_Cluster"], palette="coolwarm")
+        st.pyplot(plt)
+    
+    elif selected_algo == "PCA":
+        st.subheader("PCA Visualization")
+        pca = PCA(n_components=2)
+        pca_result = pca.fit_transform(df.iloc[:, :-1])
+        plt.scatter(pca_result[:, 0], pca_result[:, 1], c=df["DBSCAN_Cluster"], cmap="plasma")
+        plt.xlabel("PCA Component 1")
+        plt.ylabel("PCA Component 2")
+        st.pyplot(plt)
+    
+    elif selected_algo == "t-SNE":
+        st.subheader("t-SNE Visualization")
+        plt.figure(figsize=(8,5))
+        sns.scatterplot(x=df["TSNE1"], y=df["TSNE2"], hue=df["DBSCAN_Cluster"], palette="coolwarm")
+        st.pyplot(plt)
+
+def main():
+    st.sidebar.title("Navigation")
+    pages = {
+        "🏠 Home": home_page,
+        "📊 Dataset": dataset_page,
+        "📈 Visualizations": visualization_page,
+    }
+    
+    choice = st.sidebar.radio("Go to", list(pages.keys()))
+    pages[choice]()
+    
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,7 @@
+pandas
+streamlit
+numpy
+matplotlib
+seaborn
+scikit-learn
+joblib