diff --git a/exercises/02450Toolbox_Python/Scripts/ex2_1_1.py b/exercises/02450Toolbox_Python/Scripts/ex2_1_1.py
index 2a35baa91427f3c98540d03a7b7fe8026800ed36..dea5b3f9d071dbfe5fc62042a0708269e31523c1 100644
--- a/exercises/02450Toolbox_Python/Scripts/ex2_1_1.py
+++ b/exercises/02450Toolbox_Python/Scripts/ex2_1_1.py
@@ -5,7 +5,7 @@ x = np.array([-0.68, -2.11, 2.39, 0.26, 1.46, 1.33, 1.03, -0.41, -0.33, 0.47])
# Compute values
mean_x = x.mean()
-std_x = x.std(ddof=1)
+std_x = x.std(ddof=1) # ddof: Delta Degrees of freedom
median_x = np.median(x)
range_x = x.max() - x.min()
@@ -16,4 +16,4 @@ print("Standard Deviation:", std_x)
print("Median:", median_x)
print("Range:", range_x)
-print("Ran Exercise 2.1.1")
+print("Ran Exercise 2.1.1")
\ No newline at end of file
diff --git a/exercises/02450Toolbox_Python/Scripts/ex2_2_1.py b/exercises/02450Toolbox_Python/Scripts/ex2_2_1.py
index f95d6278ae22613d56fa7c9ff8bc350f6ab369cd..1def1efde521b1ba27c3465cc9192c65c9a9d7d1 100644
--- a/exercises/02450Toolbox_Python/Scripts/ex2_2_1.py
+++ b/exercises/02450Toolbox_Python/Scripts/ex2_2_1.py
@@ -12,7 +12,7 @@ filename = importlib_resources.files("dtuimldmtools").joinpath("data/digits.mat"
i = 1
# Similarity: 'SMC', 'Jaccard', 'ExtendedJaccard', 'Cosine', 'Correlation'
-similarity_measure = "SMC"
+similarity_measure = "Jaccard"
# Load the digits
# Load Matlab data file to python dict structure
@@ -32,7 +32,6 @@ sim = sim.tolist()[0]
# Tuples of sorted similarities and their indices
sim_to_index = sorted(zip(sim, noti))
-
# Visualize query image and 5 most/least similar images
plt.figure(figsize=(12, 8))
plt.subplot(3, 1, 1)
@@ -82,4 +81,4 @@ for ms in range(5):
plt.show()
-print("Ran Exercise 2.2.1")
+print("Ran Exercise 2.2.1")
\ No newline at end of file
diff --git a/exercises/02450Toolbox_Python/Scripts/ex2_2_2.py b/exercises/02450Toolbox_Python/Scripts/ex2_2_2.py
index 3f249cab4bdeb1658576664c37e14eeaca4320bc..7d0e19687667dcfc340c2aec220966040466f141 100644
--- a/exercises/02450Toolbox_Python/Scripts/ex2_2_2.py
+++ b/exercises/02450Toolbox_Python/Scripts/ex2_2_2.py
@@ -1,5 +1,4 @@
# exercise 2.2.2
-
import numpy as np
from dtuimldmtools import similarity
@@ -39,4 +38,4 @@ print(
% (similarity(x, y, "cor") - similarity(b + x, y, "cor"))[0, 0]
)
-print("Ran Exercise 2.2.2")
+print("Ran Exercise 2.2.2")
\ No newline at end of file
diff --git a/exercises/02450Toolbox_Python/Scripts/ex2_3_1.py b/exercises/02450Toolbox_Python/Scripts/ex2_3_1.py
index 7a3afe602a2df9cd90c857e3e88f805360daeca4..ea2e8d92ddd892b2a2bd5e98f605c9f3b5a5d742 100644
--- a/exercises/02450Toolbox_Python/Scripts/ex2_3_1.py
+++ b/exercises/02450Toolbox_Python/Scripts/ex2_3_1.py
@@ -1,5 +1,4 @@
# exercise 2.3.1
-
import importlib_resources
import numpy as np
import xlrd
@@ -30,4 +29,4 @@ N = len(y)
M = len(attributeNames)
C = len(classNames)
-print("Ran Exercise 2.3.1")
+print("Ran Exercise 2.3.1 - loading the Iris data")
\ No newline at end of file
diff --git a/exercises/02450Toolbox_Python/Scripts/ex2_3_2.py b/exercises/02450Toolbox_Python/Scripts/ex2_3_2.py
index 0136f799fbb17c0ae785db023c8372b618ba674a..b2b786cf46a93cd911e7d6f237cdd0a30f180ffb 100644
--- a/exercises/02450Toolbox_Python/Scripts/ex2_3_2.py
+++ b/exercises/02450Toolbox_Python/Scripts/ex2_3_2.py
@@ -2,17 +2,17 @@
import numpy as np
# (requires data from exercise 2.3.1 so will run that script first)
from ex2_3_1 import *
-from matplotlib.pyplot import figure, hist, show, subplot, xlabel, ylim
+import matplotlib.pyplot as plt
-figure(figsize=(8, 7))
+plt.figure(figsize=(8, 7))
u = np.floor(np.sqrt(M))
v = np.ceil(float(M) / u)
for i in range(M):
- subplot(int(u), int(v), i + 1)
- hist(X[:, i], color=(0.2, 0.8 - i * 0.2, 0.4))
- xlabel(attributeNames[i])
- ylim(0, N / 2)
+ plt.subplot(int(u), int(v), i + 1)
+ plt.hist(X[:, i], color=(0.2, 0.8 - i * 0.2, 0.4))
+ plt.xlabel(attributeNames[i])
+ plt.ylim(0, N / 2)
-show()
+plt.show()
print("Ran Exercise 2.3.2")
diff --git a/exercises/02450Toolbox_Python/Scripts/ex2_3_3.py b/exercises/02450Toolbox_Python/Scripts/ex2_3_3.py
index 437b1bf4ce6d7348db5a8485cb440c2dbc245046..ae2f56bdf0bff50eec77a313045784962c2c8fe3 100644
--- a/exercises/02450Toolbox_Python/Scripts/ex2_3_3.py
+++ b/exercises/02450Toolbox_Python/Scripts/ex2_3_3.py
@@ -1,12 +1,13 @@
# Exercise 2.3.3
# (requires data from exercise 2.3.1)
from ex2_3_1 import *
-from matplotlib.pyplot import boxplot, show, title, xticks, ylabel
+import matplotlib.pyplot as plt
-boxplot(X)
-xticks(range(1, 5), attributeNames)
-ylabel("cm")
-title("Fisher's Iris data set - boxplot")
-show()
+plt.figure()
+plt.boxplot(X)
+plt.xticks(range(1, 5), attributeNames)
+plt.ylabel("cm")
+plt.title("Fisher's Iris data set - boxplot")
+plt.show()
print("Ran Exercise 2.3.3")
diff --git a/exercises/02450Toolbox_Python/Scripts/ex2_3_4.py b/exercises/02450Toolbox_Python/Scripts/ex2_3_4.py
index 5a33d4d310d32f1a8774985f1e72b70cafd469a0..ce1e39cc4562be51e35fe2a9ed44cfbab8bdd511 100644
--- a/exercises/02450Toolbox_Python/Scripts/ex2_3_4.py
+++ b/exercises/02450Toolbox_Python/Scripts/ex2_3_4.py
@@ -1,24 +1,24 @@
# Exercise 2.3.4
# requires data from exercise 4.1.1
from ex2_3_1 import *
-from matplotlib.pyplot import boxplot, figure, show, subplot, title, xticks, ylim
+import matplotlib.pyplot as plt
-figure(figsize=(14, 7))
+plt.figure(figsize=(14, 7))
for c in range(C):
- subplot(1, C, c + 1)
+ plt.subplot(1, C, c + 1)
class_mask = y == c # binary mask to extract elements of class c
# or: class_mask = nonzero(y==c)[0].tolist()[0] # indices of class c
- boxplot(X[class_mask, :])
+ plt.boxplot(X[class_mask, :])
# title('Class: {0}'.format(classNames[c]))
- title("Class: " + classNames[c])
- xticks(
+ plt.title("Class: " + classNames[c])
+ plt.xticks(
range(1, len(attributeNames) + 1), [a[:7] for a in attributeNames], rotation=45
)
y_up = X.max() + (X.max() - X.min()) * 0.1
y_down = X.min() - (X.max() - X.min()) * 0.1
- ylim(y_down, y_up)
+ plt.ylim(y_down, y_up)
-show()
+plt.show()
print("Ran Exercise 2.3.4")
diff --git a/exercises/02450Toolbox_Python/Scripts/ex2_3_5.py b/exercises/02450Toolbox_Python/Scripts/ex2_3_5.py
index e2b9836da15cc13d02a1fce4b3998c319f309905..93b51ddbeacabf244e8fd127f882128d59041365 100644
--- a/exercises/02450Toolbox_Python/Scripts/ex2_3_5.py
+++ b/exercises/02450Toolbox_Python/Scripts/ex2_3_5.py
@@ -1,36 +1,26 @@
# Exercise 2.3.5
# (requires data from exercise 2.3.1)
from ex2_3_1 import *
-from matplotlib.pyplot import (
- figure,
- legend,
- plot,
- show,
- subplot,
- xlabel,
- xticks,
- ylabel,
- yticks,
-)
+import matplotlib.pyplot as plt
-figure(figsize=(12, 10))
+plt.figure(figsize=(12, 10))
for m1 in range(M):
for m2 in range(M):
- subplot(M, M, m1 * M + m2 + 1)
+ plt.subplot(M, M, m1 * M + m2 + 1)
for c in range(C):
class_mask = y == c
- plot(np.array(X[class_mask, m2]), np.array(X[class_mask, m1]), ".")
+ plt.plot(np.array(X[class_mask, m2]), np.array(X[class_mask, m1]), ".")
if m1 == M - 1:
- xlabel(attributeNames[m2])
+ plt.xlabel(attributeNames[m2])
else:
- xticks([])
+ plt.xticks([])
if m2 == 0:
- ylabel(attributeNames[m1])
+ plt.ylabel(attributeNames[m1])
else:
- yticks([])
+ plt.yticks([])
-legend(classNames)
+plt.legend(classNames)
-show()
+plt.show()
print("Ran Exercise 2.3.5")
diff --git a/exercises/02450Toolbox_Python/Scripts/ex2_3_6.py b/exercises/02450Toolbox_Python/Scripts/ex2_3_6.py
index 5684aa7d2b531df4da4ee32afc331764fc08993d..b8cec6e9303f999423bcec64332035a84066b3ee 100644
--- a/exercises/02450Toolbox_Python/Scripts/ex2_3_6.py
+++ b/exercises/02450Toolbox_Python/Scripts/ex2_3_6.py
@@ -1,15 +1,14 @@
# Exercise 2.3.6
-
-# requires data from exercise 2.3.1
+# (requires data from exercise 2.3.1)
from ex2_3_1 import *
-from matplotlib.pyplot import figure, show
+import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
# Indices of the variables to plot
ind = [0, 1, 2]
colors = ["blue", "green", "red"]
-f = figure()
+f = plt.figure()
ax = f.add_subplot(111, projection="3d") # Here the mpl_toolkits is used
for c in range(C):
class_mask = y == c
@@ -22,6 +21,6 @@ ax.set_xlabel(attributeNames[ind[0]])
ax.set_ylabel(attributeNames[ind[1]])
ax.set_zlabel(attributeNames[ind[2]])
-show()
+plt.show()
print("Ran Exercise 2.3.6")
diff --git a/exercises/02450Toolbox_Python/Scripts/ex2_3_7.py b/exercises/02450Toolbox_Python/Scripts/ex2_3_7.py
index 587367dc2b5e6c9ea0b49ded847561fb485fea49..891252345c9919dc0d3cbbbd5f83210f1ff9aa39 100644
--- a/exercises/02450Toolbox_Python/Scripts/ex2_3_7.py
+++ b/exercises/02450Toolbox_Python/Scripts/ex2_3_7.py
@@ -1,30 +1,19 @@
# Exercise 2.3.7
-
-# requires data from exercise 2.3.7
+# (requires data from exercise 2.3.1)
from ex2_3_1 import *
-from matplotlib.pyplot import (
- cm,
- colorbar,
- figure,
- imshow,
- show,
- title,
- xlabel,
- xticks,
- ylabel,
-)
+import matplotlib.pyplot as plt
from scipy.stats import zscore
X_standarized = zscore(X, ddof=1)
-figure(figsize=(12, 6))
-imshow(X_standarized, interpolation="none", aspect=(4.0 / N), cmap=cm.gray)
-xticks(range(4), attributeNames)
-xlabel("Attributes")
-ylabel("Data objects")
-title("Fisher's Iris data matrix")
-colorbar()
+plt.figure(figsize=(12, 6))
+plt.imshow(X_standarized, interpolation="none", aspect=(4.0 / N), cmap=plt.cm.gray)
+plt.xticks(range(4), attributeNames)
+plt.xlabel("Attributes")
+plt.ylabel("Data objects")
+plt.title("Fisher's Iris data matrix")
+plt.colorbar()
-show()
+plt.show()
-print("Ran Exercise 2.3.7")
+print("Ran Exercise 2.3.7")
\ No newline at end of file
diff --git a/exercises/02450Toolbox_Python/Scripts/ex2_4_1.py b/exercises/02450Toolbox_Python/Scripts/ex2_4_1.py
index 3bbc0bd0e807b369a257bcc37364ade22759066b..3b88f6b2ea4b724f696b52a31f37b729ed923b2d 100644
--- a/exercises/02450Toolbox_Python/Scripts/ex2_4_1.py
+++ b/exercises/02450Toolbox_Python/Scripts/ex2_4_1.py
@@ -1,19 +1,10 @@
# exercise 2.4.1
-
+"""
+Note: This is a long script. You may want to use breakpoint
+"""
import importlib_resources
import numpy as np
-from matplotlib.pyplot import (
- boxplot,
- figure,
- hist,
- show,
- subplot,
- title,
- xlabel,
- xticks,
- ylim,
- yticks,
-)
+import matplotlib.pyplot as plt
from scipy.io import loadmat
from scipy.stats import zscore
@@ -29,56 +20,61 @@ N = mat_data["N"][0, 0]
attributeNames = [name[0][0] for name in mat_data["attributeNames"]]
classNames = [cls[0][0] for cls in mat_data["classNames"]]
+print("Data loaded")
+
# We start with a box plot of each attribute
-figure()
-title("Wine: Boxplot")
-boxplot(X)
-xticks(range(1, M + 1), attributeNames, rotation=45)
+plt.figure()
+plt.title("Wine: Boxplot")
+plt.boxplot(X)
+plt.xticks(range(1, M + 1), attributeNames, rotation=45)
# From this it is clear that there are some outliers in the Alcohol
# attribute (10x10^14 is clearly not a proper value for alcohol content)
# However, it is impossible to see the distribution of the data, because
# the axis is dominated by these extreme outliers. To avoid this, we plot a
# box plot of standardized data (using the zscore function).
-figure(figsize=(12, 6))
-title("Wine: Boxplot (standarized)")
-boxplot(zscore(X, ddof=1), attributeNames)
-xticks(range(1, M + 1), attributeNames, rotation=45)
+plt.figure(figsize=(12, 6))
+plt.title("Wine: Boxplot (standarized)")
+plt.boxplot(zscore(X, ddof=1), attributeNames)
+plt.xticks(range(1, M + 1), attributeNames, rotation=45)
# This plot reveals that there are clearly some outliers in the Volatile
# acidity, Density, and Alcohol attributes, i.e. attribute number 2, 8,
# and 11.
+plt.show()
# Next, we plot histograms of all attributes.
-figure(figsize=(14, 9))
+plt.figure(figsize=(14, 9))
u = np.floor(np.sqrt(M))
v = np.ceil(float(M) / u)
for i in range(M):
- subplot(int(u), int(v), i + 1)
- hist(X[:, i])
- xlabel(attributeNames[i])
- ylim(0, N) # Make the y-axes equal for improved readability
+ plt.subplot(int(u), int(v), i + 1)
+ plt.hist(X[:, i])
+ plt.xlabel(attributeNames[i])
+ plt.ylim(0, N) # Make the y-axes equal for improved readability
if i % v != 0:
- yticks([])
+ plt.yticks([])
if i == 0:
- title("Wine: Histogram")
+ plt.title("Wine: Histogram")
+plt.show()
# This confirms our belief about outliers in attributes 2, 8, and 11.
# To take a closer look at this, we next plot histograms of the
# attributes we suspect contains outliers
-figure(figsize=(14, 9))
+plt.figure(figsize=(14, 9))
m = [1, 7, 10]
for i in range(len(m)):
- subplot(1, len(m), i + 1)
- hist(X[:, m[i]], 50)
- xlabel(attributeNames[m[i]])
- ylim(0, N) # Make the y-axes equal for improved readability
+ plt.subplot(1, len(m), i + 1)
+ plt.hist(X[:, m[i]], 50)
+ plt.xlabel(attributeNames[m[i]])
+ plt.ylim(0, N) # Make the y-axes equal for improved readability
if i > 0:
- yticks([])
+ plt.yticks([])
if i == 0:
- title("Wine: Histogram (selected attributes)")
+ plt.title("Wine: Histogram (selected attributes)")
+plt.show()
# The histograms show that there are a few very extreme values in these
# three attributes. To identify these values as outliers, we must use our
@@ -95,25 +91,24 @@ X = X[valid_mask, :]
y = y[valid_mask]
N = len(y)
-
# Now, we can repeat the process to see if there are any more outliers
# present in the data. We take a look at a histogram of all attributes:
-figure(figsize=(14, 9))
+plt.figure(figsize=(14, 9))
u = np.floor(np.sqrt(M))
v = np.ceil(float(M) / u)
for i in range(M):
- subplot(int(u), int(v), i + 1)
- hist(X[:, i])
- xlabel(attributeNames[i])
- ylim(0, N) # Make the y-axes equal for improved readability
+ plt.subplot(int(u), int(v), i + 1)
+ plt.hist(X[:, i])
+ plt.xlabel(attributeNames[i])
+ plt.ylim(0, N) # Make the y-axes equal for improved readability
if i % v != 0:
- yticks([])
+ plt.yticks([])
if i == 0:
- title("Wine: Histogram (after outlier detection)")
+ plt.title("Wine: Histogram (after outlier detection)")
# This reveals no further outliers, and we conclude that all outliers have
# been detected and removed.
-show()
+plt.show()
print("Ran Exercise 2.4.1")
diff --git a/exercises/02450Toolbox_Python/Scripts/ex2_4_2.py b/exercises/02450Toolbox_Python/Scripts/ex2_4_2.py
index 3c362f0b8b82eecfe3951f2c6c99722d8e10223b..9a5e241262b0b0cdb768cedea88e66f5902cf0d3 100644
--- a/exercises/02450Toolbox_Python/Scripts/ex2_4_2.py
+++ b/exercises/02450Toolbox_Python/Scripts/ex2_4_2.py
@@ -2,19 +2,10 @@
import importlib_resources
import numpy as np
-from matplotlib.pyplot import (
- figure,
- legend,
- plot,
- show,
- subplot,
- xlabel,
- xticks,
- ylabel,
- yticks,
-)
+import matplotlib.pyplot as plt
from scipy.io import loadmat
from scipy.stats import zscore
+from dtuimldmtools import similarity
filename = importlib_resources.files("dtuimldmtools").joinpath("data/wine.mat")
@@ -49,24 +40,24 @@ Xnorm = zscore(X, ddof=1)
Attributes = [1, 4, 5, 6]
NumAtr = len(Attributes)
-figure(figsize=(12, 12))
+plt.figure(figsize=(12, 12))
for m1 in range(NumAtr):
for m2 in range(NumAtr):
- subplot(NumAtr, NumAtr, m1 * NumAtr + m2 + 1)
+ plt.subplot(NumAtr, NumAtr, m1 * NumAtr + m2 + 1)
for c in range(C):
class_mask = y == c
- plot(X[class_mask, Attributes[m2]], X[class_mask, Attributes[m1]], ".")
+ plt.plot(X[class_mask, Attributes[m2]], X[class_mask, Attributes[m1]], ".")
if m1 == NumAtr - 1:
- xlabel(attributeNames[Attributes[m2]])
+ plt.xlabel(attributeNames[Attributes[m2]])
else:
- xticks([])
+ plt.xticks([])
if m2 == 0:
- ylabel(attributeNames[Attributes[m1]])
+ plt.ylabel(attributeNames[Attributes[m1]])
else:
- yticks([])
+ plt.yticks([])
# ylim(0,X.max()*1.1)
# xlim(0,X.max()*1.1)
-legend(classNames)
-show()
+plt.legend(classNames)
+plt.show()
-print("Ran Exercise 2.4.2")
+print("Ran Exercise 2.4.2")
\ No newline at end of file