iter

Author: glemaitre

examples/over-sampling/plot_comparison_over_sampling.py

@@ -25,6 +25,9 @@
 
 
 # %%
+from sklearn.datasets import make_classification
+
+
 def create_dataset(
     n_samples=1000,
     weights=(0.01, 0.01, 0.98),

examples/under-sampling/plot_illustration_nearmiss.py

@@ -7,6 +7,9 @@
 
 """
 
+# Authors: Guillaume Lemaitre <[email protected]>
+# License: MIT
+
 import matplotlib.pyplot as plt
 import numpy as np
 

examples/under-sampling/plot_illustration_tomek_links.py

@@ -4,61 +4,72 @@
 ==============================================
 
 This example illustrates what is a Tomek link.
-
 """
 
-import matplotlib.pyplot as plt
-import numpy as np
-
-from imblearn.under_sampling import TomekLinks
+# Authors: Guillaume Lemaitre <[email protected]>
+# License: MIT
 
+# %%
 print(__doc__)
 
-rng = np.random.RandomState(18)
+import matplotlib.pyplot as plt
+import seaborn as sns
 
-###############################################################################
+sns.set_context("poster")
+
+# %% [markdown]
 # This function allows to make nice plotting
 
+# %%
+
 
 def make_plot_despine(ax):
-    ax.spines["top"].set_visible(False)
-    ax.spines["right"].set_visible(False)
-    ax.get_xaxis().tick_bottom()
-    ax.get_yaxis().tick_left()
-    ax.spines["left"].set_position(("outward", 10))
-    ax.spines["bottom"].set_position(("outward", 10))
-    ax.set_xlim([0.0, 3.5])
-    ax.set_ylim([0.0, 3.5])
+    sns.despine(ax=ax, offset=10)
+    # ax.axis("square")
+    ax.set_xlim([0, 3])
+    ax.set_ylim([0, 3])
     ax.set_xlabel(r"$X_1$")
     ax.set_ylabel(r"$X_2$")
-    ax.legend()
+    ax.legend(loc="lower right")
 
 
-###############################################################################
-# Generate some data with one Tomek link
+# %% [markdown]
+# We will generate some toy data that illustrates how
+# :class:`~imblearn.under_sampling.TomekLinks` is used to clean a dataset.
+
+# %%
+import numpy as np
+
+rng = np.random.RandomState(18)
 
-# minority class
 X_minority = np.transpose(
     [[1.1, 1.3, 1.15, 0.8, 0.55, 2.1], [1.0, 1.5, 1.7, 2.5, 0.55, 1.9]]
 )
-# majority class
 X_majority = np.transpose(
     [
         [2.1, 2.12, 2.13, 2.14, 2.2, 2.3, 2.5, 2.45],
         [1.5, 2.1, 2.7, 0.9, 1.0, 1.4, 2.4, 2.9],
     ]
 )
 
-###############################################################################
+# %% [markdown]
 # In the figure above, the samples highlighted in green form a Tomek link since
-# they are of different classes and are nearest neighbours of each other.
+# they are of different classes and are nearest neighbors of each other.
 
-fig, ax = plt.subplots(1, 1, figsize=(6, 6))
+fig, ax = plt.subplots(figsize=(8, 8))
 ax.scatter(
-    X_minority[:, 0], X_minority[:, 1], label="Minority class", s=200, marker="_",
+    X_minority[:, 0],
+    X_minority[:, 1],
+    label="Minority class",
+    s=200,
+    marker="_",
 )
 ax.scatter(
-    X_majority[:, 0], X_majority[:, 1], label="Majority class", s=200, marker="+",
+    X_majority[:, 0],
+    X_majority[:, 1],
+    label="Majority class",
+    s=200,
+    marker="+",
 )
 
 # highlight the samples of interest
@@ -69,27 +80,27 @@ def make_plot_despine(ax):
     s=200,
     alpha=0.3,
 )
-ax.set_title("Illustration of a Tomek link")
 make_plot_despine(ax)
+fig.suptitle("Illustration of a Tomek link")
 fig.tight_layout()
 
-###############################################################################
-# We can run the ``TomekLinks`` sampling to remove the corresponding
-# samples. If ``sampling_strategy='auto'`` only the sample from the majority
-# class will be removed. If ``sampling_strategy='all'`` both samples will be
-# removed.
+# %% [markdown]
+# We can run the :class:`~imblearn.under_sampling.TomekLinks` sampling to
+# remove the corresponding samples. If `sampling_strategy='auto'` only the
+# sample from the majority class will be removed. If `sampling_strategy='all'`
+# both samples will be removed.
+
+# %%
+from imblearn.under_sampling import TomekLinks
 
-sampler = TomekLinks()
+fig, axs = plt.subplots(nrows=1, ncols=2, figsize=(16, 8))
 
-fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(12, 6))
+samplers = {
+    "Removing only majority samples": TomekLinks(sampling_strategy="auto"),
+    "Removing all samples": TomekLinks(sampling_strategy="all"),
+}
 
-ax_arr = (ax1, ax2)
-title_arr = ("Removing only majority samples", "Removing all samples")
-for ax, title, sampler in zip(
-    ax_arr,
-    title_arr,
-    [TomekLinks(sampling_strategy="auto"), TomekLinks(sampling_strategy="all")],
-):
+for ax, (title, sampler) in zip(axs, samplers.items()):
     X_res, y_res = sampler.fit_resample(
         np.vstack((X_minority, X_majority)),
         np.array([0] * X_minority.shape[0] + [1] * X_majority.shape[0]),
@@ -123,3 +134,5 @@ def make_plot_despine(ax):
 fig.tight_layout()
 
 plt.show()
+
+# %%