ML6 added

ML/ML6.md

@@ -0,0 +1,75 @@
+```
+import pandas as pd
+import matplotlib.pyplot as plt
+from sklearn.preprocessing import StandardScaler
+from sklearn.cluster import KMeans
+from scipy.cluster.hierarchy import linkage, dendrogram, fcluster
+import seaborn as sns
+
+
+df = pd.read_csv("sales_data_sample.csv", encoding='latin1', on_bad_lines='skip')
+print("Dataset shape:", df.shape)
+print(df.head())
+
+
+X = df.select_dtypes(include=['int64', 'float64'])
+print("Features used for clustering:\n", X.head())
+
+# Select relevant numeric columns
+# X = df[['SALES', 'QUANTITYORDERED', 'PRICEEACH']]
+
+# Handle missing values if any
+# X = features.dropna()
+
+
+scaler = StandardScaler()
+X_scaled = scaler.fit_transform(X)
+
+
+# Determine optimal number of clusters using Elbow Method
+wcss = []
+for k in range(1, 11):
+    kmeans = KMeans(n_clusters=k, random_state=42)
+    kmeans.fit(X_scaled)
+    wcss.append(kmeans.inertia_)
+
+# Plot Elbow Method
+plt.figure(figsize=(6,4))
+plt.plot(range(1, 11), wcss, marker='o')
+plt.title('Elbow Method')
+plt.xlabel('Number of clusters (k)')
+plt.ylabel('Inertia (WCSS)')
+plt.show()
+
+# Fit KMeans with chosen number of clusters (example: 3 clusters)
+kmeans = KMeans(n_clusters=3, random_state=42) # Add n_init=10 param in the function to suppress warnings
+clusters_kmeans = kmeans.fit_predict(X_scaled)
+df['KMeans_Cluster'] = clusters_kmeans
+
+# Visualize clusters
+sns.scatterplot(x='SALES', y='PRICEEACH', hue='KMeans_Cluster', data=df, palette='viridis')
+plt.title("K-Means Clustering")
+plt.show()
+
+print("\nK-Means Cluster Centers:\n", kmeans.cluster_centers_)
+print("\nCluster counts:\n", df['KMeans_Cluster'].value_counts())
+
+
+# Create linkage matrix
+Z = linkage(X_scaled, method='ward')
+
+# Plot dendrogram
+plt.figure(figsize=(10,5))
+dendrogram(Z)
+plt.title('Hierarchical Clustering Dendrogram')
+plt.xlabel('Samples')
+plt.ylabel('Distance')
+plt.show()
+
+# Assign clusters (example: 3 clusters)
+clusters_hier = fcluster(Z, t=3, criterion='maxclust')
+df['Hierarchical_Cluster'] = clusters_hier
+
+print("\nHierarchical Cluster counts:\n", pd.Series(clusters_hier).value_counts())
+
+```