#!/usr/bin/env python
# coding: utf-8

# In[1]:


get_ipython().run_line_magic('matplotlib', 'inline')


# # Plotting Decision Regions

# A function for plotting decision regions of classifiers in 1 or 2 dimensions.

# > from mlxtend.plotting import plot_decision_regions

# ### References
# 
# - 

# ## Example 1 - Decision regions in 2D

# In[2]:


from mlxtend.plotting import plot_decision_regions
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.svm import SVC

# Loading some example data
iris = datasets.load_iris()
X = iris.data[:, [0, 2]]
y = iris.target

# Training a classifier
svm = SVC(C=0.5, kernel='linear')
svm.fit(X, y)


# Plotting decision regions
plot_decision_regions(X, y, clf=svm, legend=2)

# Adding axes annotations
plt.xlabel('sepal length [cm]')
plt.ylabel('petal length [cm]')
plt.title('SVM on Iris')
plt.show()


# ## Example 2 - Decision regions in 1D

# In[3]:


from mlxtend.plotting import plot_decision_regions
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.svm import SVC

# Loading some example data
iris = datasets.load_iris()
X = iris.data[:, 2]
X = X[:, None]
y = iris.target

# Training a classifier
svm = SVC(C=0.5, kernel='linear')
svm.fit(X, y)

# Plotting decision regions
plot_decision_regions(X, y, clf=svm, legend=2)

# Adding axes annotations
plt.xlabel('sepal length [cm]')
plt.title('SVM on Iris')

plt.show()


# ## Example 3 - Decision Region Grids

# In[4]:


from sklearn.linear_model import LogisticRegression
from sklearn.naive_bayes import GaussianNB 
from sklearn.ensemble import RandomForestClassifier
from sklearn.svm import SVC
from sklearn import datasets
import numpy as np

# Initializing Classifiers
clf1 = LogisticRegression(random_state=1)
clf2 = RandomForestClassifier(random_state=1)
clf3 = GaussianNB()
clf4 = SVC()

# Loading some example data
iris = datasets.load_iris()
X = iris.data[:, [0,2]]
y = iris.target


# In[5]:


import matplotlib.pyplot as plt
from mlxtend.plotting import plot_decision_regions
import matplotlib.gridspec as gridspec
import itertools
gs = gridspec.GridSpec(2, 2)

fig = plt.figure(figsize=(10,8))

labels = ['Logistic Regression', 'Random Forest', 'Naive Bayes', 'SVM']
for clf, lab, grd in zip([clf1, clf2, clf3, clf4],
                         labels,
                         itertools.product([0, 1], repeat=2)):

    clf.fit(X, y)
    ax = plt.subplot(gs[grd[0], grd[1]])
    fig = plot_decision_regions(X=X, y=y, clf=clf, legend=2)
    plt.title(lab)
    
plt.show()


# ## Example 4 - Highlighting Test Data Points

# In[6]:


from mlxtend.plotting import plot_decision_regions
from mlxtend.preprocessing import shuffle_arrays_unison
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.svm import SVC


# Loading some example data
iris = datasets.load_iris()
X, y = iris.data[:, [0,2]], iris.target
X, y = shuffle_arrays_unison(arrays=[X, y], random_seed=3)

X_train, y_train = X[:100], y[:100]
X_test, y_test = X[100:], y[100:]

# Training a classifier
svm = SVC(C=0.5, kernel='linear')
svm.fit(X_train, y_train)

# Plotting decision regions
plot_decision_regions(X, y, clf=svm, legend=2, 
                      X_highlight=X_test)

# Adding axes annotations
plt.xlabel('sepal length [cm]')
plt.ylabel('petal length [cm]')
plt.title('SVM on Iris')
plt.show()


# ## Example 5 - Evaluating Classifier Behavior on Non-Linear Problems

# In[7]:


from sklearn.linear_model import LogisticRegression
from sklearn.naive_bayes import GaussianNB 
from sklearn.ensemble import RandomForestClassifier
from sklearn.svm import SVC

# Initializing Classifiers
clf1 = LogisticRegression(random_state=1)
clf2 = RandomForestClassifier(n_estimators=100, 
                              random_state=1)
clf3 = GaussianNB()
clf4 = SVC()


# In[8]:


# Loading Plotting Utilities
import matplotlib.pyplot as plt
import matplotlib.gridspec as gridspec
import itertools
from mlxtend.plotting import plot_decision_regions
import numpy as np


# ### XOR

# In[9]:


xx, yy = np.meshgrid(np.linspace(-3, 3, 50),
                     np.linspace(-3, 3, 50))
rng = np.random.RandomState(0)
X = rng.randn(300, 2)
y = np.array(np.logical_xor(X[:, 0] > 0, X[:, 1] > 0), 
             dtype=int)


# In[10]:


gs = gridspec.GridSpec(2, 2)

fig = plt.figure(figsize=(10,8))

labels = ['Logistic Regression', 'Random Forest', 'Naive Bayes', 'SVM']
for clf, lab, grd in zip([clf1, clf2, clf3, clf4],
                         labels,
                         itertools.product([0, 1], repeat=2)):

    clf.fit(X, y)
    ax = plt.subplot(gs[grd[0], grd[1]])
    fig = plot_decision_regions(X=X, y=y, clf=clf, legend=2)
    plt.title(lab)

plt.show()


# ### Half-Moons

# In[11]:


from sklearn.datasets import make_moons
X, y = make_moons(n_samples=100, random_state=123)

gs = gridspec.GridSpec(2, 2)

fig = plt.figure(figsize=(10,8))

labels = ['Logistic Regression', 'Random Forest', 'Naive Bayes', 'SVM']
for clf, lab, grd in zip([clf1, clf2, clf3, clf4],
                         labels,
                         itertools.product([0, 1], repeat=2)):

    clf.fit(X, y)
    ax = plt.subplot(gs[grd[0], grd[1]])
    fig = plot_decision_regions(X=X, y=y, clf=clf, legend=2)
    plt.title(lab)

plt.show()


# ### Concentric Circles

# In[12]:


from sklearn.datasets import make_circles
X, y = make_circles(n_samples=1000, random_state=123, noise=0.1, factor=0.2)

gs = gridspec.GridSpec(2, 2)

fig = plt.figure(figsize=(10,8))

labels = ['Logistic Regression', 'Random Forest', 'Naive Bayes', 'SVM']
for clf, lab, grd in zip([clf1, clf2, clf3, clf4],
                         labels,
                         itertools.product([0, 1], repeat=2)):

    clf.fit(X, y)
    ax = plt.subplot(gs[grd[0], grd[1]])
    fig = plot_decision_regions(X=X, y=y, clf=clf, legend=2)
    plt.title(lab)

plt.show()


# ## Example 6 - Working with existing axes objects using subplots

# In[13]:


import matplotlib.pyplot as plt
from mlxtend.plotting import plot_decision_regions

from sklearn.linear_model import LogisticRegression
from sklearn.naive_bayes import GaussianNB 
from sklearn import datasets
import numpy as np

# Loading some example data
iris = datasets.load_iris()
X = iris.data[:, 2]
X = X[:, None]
y = iris.target

# Initializing and fitting classifiers
clf1 = LogisticRegression(random_state=1)
clf2 = GaussianNB()
clf1.fit(X, y)
clf2.fit(X, y)

fig, axes = plt.subplots(1, 2, figsize=(10, 3))

fig = plot_decision_regions(X=X, y=y, clf=clf1, ax=axes[0], legend=2)
fig = plot_decision_regions(X=X, y=y, clf=clf2, ax=axes[1], legend=1)
    
plt.show()


# ## Example 7 - Decision regions with more than two training features

# In[14]:


from mlxtend.plotting import plot_decision_regions
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.svm import SVC

# Loading some example data
X, y = datasets.make_blobs(n_samples=600, n_features=3,
                           centers=[[2, 2, -2],[-2, -2, 2]],
                           cluster_std=[2, 2], random_state=2)

# Training a classifier
svm = SVC()
svm.fit(X, y)

# Plotting decision regions
fig, ax = plt.subplots()
# Decision region for feature 3 = 1.5
value = 1.5
# Plot training sample with feature 3 = 1.5 +/- 0.75
width = 0.75
plot_decision_regions(X, y, clf=svm,
                      filler_feature_values={2: value},
                      filler_feature_ranges={2: width},
                      legend=2, ax=ax)
ax.set_xlabel('Feature 1')
ax.set_ylabel('Feature 2')
ax.set_title('Feature 3 = {}'.format(value))

# Adding axes annotations
fig.suptitle('SVM on make_blobs')
plt.show()


# ## Example 8 - Grid of decision region slices

# In[15]:


from mlxtend.plotting import plot_decision_regions
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.svm import SVC

# Loading some example data
X, y = datasets.make_blobs(n_samples=500, n_features=3, centers=[[2, 2, -2],[-2, -2, 2]],
                           cluster_std=[2, 2], random_state=2)

# Training a classifier
svm = SVC()
svm.fit(X, y)

# Plotting decision regions
fig, axarr = plt.subplots(2, 2, figsize=(10,8), sharex=True, sharey=True)
values = [-4.0, -1.0, 1.0, 4.0]
width = 0.75
for value, ax in zip(values, axarr.flat):
    plot_decision_regions(X, y, clf=svm,
                          filler_feature_values={2: value},
                          filler_feature_ranges={2: width},
                          legend=2, ax=ax)
    ax.set_xlabel('Feature 1')
    ax.set_ylabel('Feature 2')
    ax.set_title('Feature 3 = {}'.format(value))

# Adding axes annotations
fig.suptitle('SVM on make_blobs')
plt.show()


# ## Example 9 - Customizing the plotting style

# In[16]:


from mlxtend.plotting import plot_decision_regions
from mlxtend.preprocessing import shuffle_arrays_unison
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.svm import SVC

# Loading some example data
iris = datasets.load_iris()
X = iris.data[:, [0, 2]]
y = iris.target
X, y = shuffle_arrays_unison(arrays=[X, y], random_seed=3)
X_train, y_train = X[:100], y[:100]
X_test, y_test = X[100:], y[100:]

# Training a classifier
svm = SVC(C=0.5, kernel='linear')
svm.fit(X_train, y_train)

# Specify keyword arguments to be passed to underlying plotting functions
scatter_kwargs = {'s': 120, 'edgecolor': None, 'alpha': 0.7}
contourf_kwargs = {'alpha': 0.2}
scatter_highlight_kwargs = {'s': 120, 'label': 'Test data', 'alpha': 0.7}
# Plotting decision regions
plot_decision_regions(X, y, clf=svm, legend=2,
                      X_highlight=X_test,
                      scatter_kwargs=scatter_kwargs,
                      contourf_kwargs=contourf_kwargs,
                      scatter_highlight_kwargs=scatter_highlight_kwargs)

# Adding axes annotations
plt.xlabel('sepal length [cm]')
plt.ylabel('petal length [cm]')
plt.title('SVM on Iris')
plt.show()


# # API

# In[1]:


with open('../../api_modules/mlxtend.plotting/plot_decision_regions.md', 'r') as f:
    print(f.read())