minor restructuring of ex4 and new ex2_4_3

exercises/02450Toolbox_Python/Scripts/ex2_4_3.py

@@ -2,9 +2,13 @@
 #%%
 ## Intro
 """
-Note: This is a long script. We suggest you run it usign the #%% feature 
+This is a small experiment where the exercise has a slightly different format than usual.
+The purpose is to explore the best format of Python exercise in the course.
+
+It is a long script. We suggest you run it usign the #%% feature 
 in VScode which allows you to easily run parts at the time in interactive mode 
-(similar to a Jupyter notebook)
+(similar to a Jupyter notebook yet still havign the full VScode/debugger available)
+
 """
 import importlib_resources
 import numpy as np
@@ -51,7 +55,6 @@ subsample_mask = np.random.choice(N, N_wines_to_consider, replace=False)
 X = X[subsample_mask, :]
 y = y[subsample_mask]
 wine_id = wine_id[subsample_mask] # this is simply so we can id the orginal winev if need be
-N = len(y)
 
 sorted_indices = np.argsort(y) # sort rows in X acording to whether they are red of white
 X = X[sorted_indices]
@@ -59,14 +62,15 @@ y = y[sorted_indices]
 wine_id = wine_id[sorted_indices]
 N = len(y)
 
+# create a list of string for the plots xticks/labels
 idx = np.arange(0,N)
 wine_id_type = [f"{a3} (id={a1} type={a2})" for a1,a2,a3 in zip(wine_id, y , idx)]
 wine_id_type_vert = [f"(id={a1} type={a2}) {a3}" for a1,a2,a3 in zip(wine_id, y , idx)]
 
 
 #%%
-## TASK D: Optionally, standardize  the attributes
-# Try, once you have complted the script, to change this and see the effect on
+## TASK D: Optionally, standardize the attributes
+# Try, once you have completed the script, to change this and see the effect on
 # the associated distance in TASK H and I
 if True:
     X = zscore(X, ddof=1)
@@ -87,13 +91,15 @@ plt.xlabel('Attributes/features')
 plt.ylabel('Observations')
 plt.show()
 
-print("Data loaded (both standardized and not standardized versions)")
+print("Data loaded")
 
 #%%
-## TASK F: Extract two wines and compute distances between a white and red whine (warm up exercise)
+## TASK F: Extract two wines and compute distances between a white and red wine (warm up exercise)
+#
+# Experiment with the various scaling factors and attributes being scale 
+# to see how the scaling affects the Lp distances (default L2)
 #
-# Experiment with the various scaling factors and attrbutes being scale to see how the 
-# scaling affects the Lp distances (default L2)
+# Note: you should think about ´x_red´ and ´x_white´ as vectors!
 #
 x_red = np.copy(X[0,:]) # note we make a copy to avoid messing with X in case we change x_white and x_red
 x_white = np.copy(X[-1,:])
@@ -137,21 +143,24 @@ red_L2 = np.linalg.norm(X - x_red, 2, axis=1)  # L_2
 red_Linf = np.linalg.norm(X - x_red, np.inf, axis=1)  # L_inf
 
 # This is not important 
-def list_in_order(alist, order):
+def list_in_order(alist, order): # credit JHW
     """Given a list 'alist' and a list of indices 'order'
-    returns the list in the order given by the indices"""
+    returns the list in the order given by the indices. Credit: JHW"""
     return [alist[i] for i in order]
 
-def rank_plot(distances):  # this is not important
+def rank_plot(distances):  # credit JHW
+    """
+    A helper function. Credit: JHW  
+    """
     order = np.argsort(distances) # find the ordering of the distances    
     ax.bar(np.arange(len(distances)), distances[order]) # bar plot them
     ax.set_xlabel("Wines / type", fontsize=12)
-    ax.set_ylabel("Distance to the first red whine", fontsize=12)
+    ax.set_ylabel("Distance to the first red wine", fontsize=12)
     ax.set_xticks(np.arange(N))
     #ax.set_frame_on(False) # remove frame
     # make sure the correct order is used for the labels!
     ax.set_xticklabels(
-        list_in_order(wine_id_type, order), rotation="vertical", fontsize=7
+        list_in_order(wine_id_type, order), rotation="vertical", fontsize=7        
     )
 
 # Make the plots (not important how this happens)
@@ -170,8 +179,9 @@ plt.tight_layout()
 
 
 #%% 
-## TASK H: Plot distances among all wines
-# Compute pairwise distances between rows and save in the following variables:
+## TASK H: Plot distances between all wines.
+# Compute all the possible pairwise distances between rows and save 
+# in the following variables:
 #
 # ´pairwise_distances_L1´: An NxN matrix with distances between row i and row j using L1
 # ´pairwise_distances_L2´: An NxN matrix with distances between row i and row j using L2
@@ -233,9 +243,9 @@ plt.show()
 # relative difference between the inter and intra wine distances (p.s. it does...). 
 #
 
-avg_interdist_white = np.nan # replace np.nan with your 
-avg_interdist_red = np.nan # replace np.nan with your 
-avg_intradist_red2white = np.nan # replace np.nan with your 
+avg_interdist_white = np.nan # replace np.nan with your estimate
+avg_interdist_red = np.nan # replace np.nan with your estimate
+avg_intradist_red2white = np.nan # replace np.nan with your estimate
 
 
 # TASK: INSERT YOUR CODE HERE