end clustering

frontend/pages/clustering.py

@@ -2,47 +2,34 @@ import streamlit as st
 from sklearn.cluster import KMeans
 import matplotlib.pyplot as plt
 
-st.header("clustering et Prediction")
+st.header("Clustering")
 
 
 if "data" in st.session_state:
     data = st.session_state.data
 
     with st.form("my_form"):
-        header = st.columns([2,1,2])
-        header[0].subheader("Dispersion")
-        header[1].subheader("Number of clusters")
-        header[2].subheader("Data Name")
+        row1 = st.columns([1,1,1])
+        n_clusters = row1[0].selectbox("Number of clusters", range(1, 10))
+        data_name = row1[1].multiselect("Data Name",data.select_dtypes(include="number").columns, max_selections=2)
+        n_init = row1[2].number_input("n_init",step=1,min_value=1)
+
+        row2 = st.columns([1,1])
+        max_iter = row1[0].number_input("max_iter",step=1,min_value=1)
 
-        row1 = st.columns([2,1,2])
-        cluster_std = row1[0].slider("", 0.2, 3.0, 0.2, 0.2)
-        n_clusters = row1[1].selectbox("", range(1, 10))
-        data_name = row1[2].selectbox("", data.columns)
 
         st.form_submit_button('launch')
 
-    from sklearn.datasets import make_blobs
-    from sklearn.cluster import KMeans
-    import matplotlib.pyplot as plt
-    import streamlit as st
-    import random
+    if len(data_name) == 2:
+        x = data[data_name].to_numpy()
 
-    # Points generator
-    x, _ = make_blobs(n_samples=200, n_features=2, centers=5, cluster_std=cluster_std, shuffle=True, random_state=10)
+        kmeans = KMeans(n_clusters=n_clusters, init='random', n_init=n_init, max_iter=max_iter, random_state=111)
+        y_kmeans = kmeans.fit_predict(x)
 
-    x = data[["Unit Price","Unit Cost"]].to_numpy()
-
-    # k-means algorithm 
-    kmeans = KMeans(n_clusters=n_clusters, init='random', n_init=10, max_iter=300, random_state=111)
-    y_kmeans = kmeans.fit_predict(x)
-
-    # Plotting colored clusters 
-    fig, ax = plt.subplots(figsize=(12,8))
-    plt.scatter(x[:, 0], x[:, 1], s=100, c=kmeans.labels_, cmap='Set1')
-    plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], s=400, marker='*', color='k')
-    st.pyplot(fig)
+        fig, ax = plt.subplots(figsize=(12,8))
+        plt.scatter(x[:, 0], x[:, 1], s=100, c=kmeans.labels_, cmap='Set1')
+        plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], s=400, marker='*', color='k')
+        st.pyplot(fig)
 
 else:
     st.error("file not loaded")
-
-# Cached function that returns a mutable object with a random number in the range 0-10