ch12

Author: rasbt

ch10/ch10.ipynb

@@ -502,15 +502,15 @@ def lin_regplot(X, y, model):
 y_quad_fit = pr.predict(quadratic.fit_transform(X_fit))
 
 # plot results
-plt.scatter(X, y, label='training points')
-plt.plot(X_fit, y_lin_fit, label='linear fit', linestyle='--')
-plt.plot(X_fit, y_quad_fit, label='quadratic fit')
+plt.scatter(X, y, label='Training points')
+plt.plot(X_fit, y_lin_fit, label='Linear fit', linestyle='--')
+plt.plot(X_fit, y_quad_fit, label='Quadratic fit')
 plt.xlabel('Explanatory variable')
 plt.ylabel('Predicted or known target values')
 plt.legend(loc='upper left')
 
 plt.tight_layout()
-plt.savefig('images/10_10.png', dpi=300)
+#plt.savefig('images/10_11.png', dpi=300)
 plt.show()
 
 
@@ -563,22 +563,22 @@ def lin_regplot(X, y, model):
 
 
 # plot results
-plt.scatter(X, y, label='training points', color='lightgray')
+plt.scatter(X, y, label='Training points', color='lightgray')
 
 plt.plot(X_fit, y_lin_fit, 
-         label='linear (d=1), $R^2=%.2f$' % linear_r2, 
+         label='Linear (d=1), $R^2=%.2f$' % linear_r2, 
          color='blue', 
          lw=2, 
          linestyle=':')
 
 plt.plot(X_fit, y_quad_fit, 
-         label='quadratic (d=2), $R^2=%.2f$' % quadratic_r2,
+         label='Quadratic (d=2), $R^2=%.2f$' % quadratic_r2,
          color='red', 
          lw=2,
          linestyle='-')
 
 plt.plot(X_fit, y_cubic_fit, 
-         label='cubic (d=3), $R^2=%.2f$' % cubic_r2,
+         label='Cubic (d=3), $R^2=%.2f$' % cubic_r2,
          color='green', 
          lw=2, 
          linestyle='--')
@@ -587,7 +587,7 @@ def lin_regplot(X, y, model):
 plt.ylabel('Price in $1000s [MEDV]')
 plt.legend(loc='upper right')
 
-#plt.savefig('images/10_11.png', dpi=300)
+#plt.savefig('images/10_12.png', dpi=300)
 plt.show()
 
 
@@ -610,10 +610,10 @@ def lin_regplot(X, y, model):
 linear_r2 = r2_score(y_sqrt, regr.predict(X_log))
 
 # plot results
-plt.scatter(X_log, y_sqrt, label='training points', color='lightgray')
+plt.scatter(X_log, y_sqrt, label='Training points', color='lightgray')
 
 plt.plot(X_fit, y_lin_fit, 
-         label='linear (d=1), $R^2=%.2f$' % linear_r2, 
+         label='Linear (d=1), $R^2=%.2f$' % linear_r2, 
          color='blue', 
          lw=2)
 
@@ -622,7 +622,7 @@ def lin_regplot(X, y, model):
 plt.legend(loc='lower left')
 
 plt.tight_layout()
-#plt.savefig('images/10_12.png', dpi=300)
+#plt.savefig('images/10_13.png', dpi=300)
 plt.show()
 
 
@@ -647,7 +647,7 @@ def lin_regplot(X, y, model):
 lin_regplot(X[sort_idx], y[sort_idx], tree)
 plt.xlabel('% lower status of the population [LSTAT]')
 plt.ylabel('Price in $1000s [MEDV]')
-#plt.savefig('images/10_13.png', dpi=300)
+#plt.savefig('images/10_14.png', dpi=300)
 plt.show()
 
 
@@ -691,15 +691,15 @@ def lin_regplot(X, y, model):
             marker='o', 
             s=35,
             alpha=0.9,
-            label='training data')
+            label='Training data')
 plt.scatter(y_test_pred,  
             y_test_pred - y_test, 
             c='limegreen',
             edgecolor='white',
             marker='s', 
             s=35,
             alpha=0.9,
-            label='test data')
+            label='Test data')
 
 plt.xlabel('Predicted values')
 plt.ylabel('Residuals')
@@ -708,7 +708,7 @@ def lin_regplot(X, y, model):
 plt.xlim([-10, 50])
 plt.tight_layout()
 
-# plt.savefig('images/10_14.png', dpi=300)
+#plt.savefig('images/10_15.png', dpi=300)
 plt.show()
 
 

ch10/ch10.py

@@ -32,7 +32,15 @@
 
 
 
-# *The use of `watermark` is optional. You can install this IPython extension via "`pip install watermark`". For more information, please see: https://github.com/rasbt/watermark.*
+# *The use of `watermark` is optional. You can install this Jupyter extension via*  
+# 
+#     conda install watermark -c conda-forge  
+# 
+# or  
+# 
+#     pip install watermark   
+# 
+# *For more information, please see: https://github.com/rasbt/watermark.*
 
 
 # ### Overview
@@ -101,22 +109,22 @@
             X[y_km == 0, 1],
             s=50, c='lightgreen',
             marker='s', edgecolor='black',
-            label='cluster 1')
+            label='Cluster 1')
 plt.scatter(X[y_km == 1, 0],
             X[y_km == 1, 1],
             s=50, c='orange',
             marker='o', edgecolor='black',
-            label='cluster 2')
+            label='Cluster 2')
 plt.scatter(X[y_km == 2, 0],
             X[y_km == 2, 1],
             s=50, c='lightblue',
             marker='v', edgecolor='black',
-            label='cluster 3')
+            label='Cluster 3')
 plt.scatter(km.cluster_centers_[:, 0],
             km.cluster_centers_[:, 1],
             s=250, marker='*',
             c='red', edgecolor='black',
-            label='centroids')
+            label='Centroids')
 plt.legend(scatterpoints=1)
 plt.grid()
 plt.tight_layout()
@@ -219,17 +227,17 @@
             c='lightgreen',
             edgecolor='black',
             marker='s',
-            label='cluster 1')
+            label='Cluster 1')
 plt.scatter(X[y_km == 1, 0],
             X[y_km == 1, 1],
             s=50,
             c='orange',
             edgecolor='black',
             marker='o',
-            label='cluster 2')
+            label='Cluster 2')
 
 plt.scatter(km.cluster_centers_[:, 0], km.cluster_centers_[:, 1],
-            s=250, marker='*', c='red', label='centroids')
+            s=250, marker='*', c='red', label='Centroids')
 plt.legend()
 plt.grid()
 plt.tight_layout()
@@ -330,7 +338,7 @@
 
 
 
-# 3. correct approach: Input sample matrix
+# 3. correct approach: Input matrix
 
 row_clusters = linkage(df.values, method='complete', metric='euclidean')
 pd.DataFrame(row_clusters,
@@ -452,15 +460,15 @@
 y_ac = ac.fit_predict(X)
 ax2.scatter(X[y_ac == 0, 0], X[y_ac == 0, 1], c='lightblue',
             edgecolor='black',
-            marker='o', s=40, label='cluster 1')
+            marker='o', s=40, label='Cluster 1')
 ax2.scatter(X[y_ac == 1, 0], X[y_ac == 1, 1], c='red',
             edgecolor='black',
-            marker='s', s=40, label='cluster 2')
+            marker='s', s=40, label='Cluster 2')
 ax2.set_title('Agglomerative clustering')
 
 plt.legend()
 plt.tight_layout()
-# plt.savefig('images/11_15.png', dpi=300)
+#plt.savefig('images/11_15.png', dpi=300)
 plt.show()
 
 
@@ -474,11 +482,11 @@
 plt.scatter(X[y_db == 0, 0], X[y_db == 0, 1],
             c='lightblue', marker='o', s=40,
             edgecolor='black', 
-            label='cluster 1')
+            label='Cluster 1')
 plt.scatter(X[y_db == 1, 0], X[y_db == 1, 1],
             c='red', marker='s', s=40,
             edgecolor='black', 
-            label='cluster 2')
+            label='Cluster 2')
 plt.legend()
 plt.tight_layout()
 #plt.savefig('images/11_16.png', dpi=300)