File size: 2,918 Bytes
ad53465 |
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 |
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()
|