Random Forest Classification¶
Importing the libraries¶
In [3]:
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
Importing the dataset¶
In [4]:
dataset = pd.read_csv('Social_Network_Ads.csv')
X = dataset.iloc[:, :-1].values
y = dataset.iloc[:, -1].values
Splitting the dataset into the Training set and Test set¶
In [5]:
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 0)
In [6]:
print(X_train[0:3])
[[ 44 39000] [ 32 120000] [ 38 50000]]
In [7]:
print(y_train[0:3])
[0 1 0]
Feature Scaling¶
In [8]:
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
In [9]:
print(X_train[0:3])
[[ 0.58164944 -0.88670699] [-0.60673761 1.46173768] [-0.01254409 -0.5677824 ]]
Training the Random Forest Classification model on the Training set¶
In [10]:
from sklearn.ensemble import RandomForestClassifier
classifier = RandomForestClassifier(n_estimators = 10, criterion = 'entropy', random_state = 0)
classifier.fit(X_train, y_train)
Out[10]:
RandomForestClassifier(criterion='entropy', n_estimators=10, random_state=0)In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
Parameters
| n_estimators | 10 | |
| criterion | 'entropy' | |
| max_depth | None | |
| min_samples_split | 2 | |
| min_samples_leaf | 1 | |
| min_weight_fraction_leaf | 0.0 | |
| max_features | 'sqrt' | |
| max_leaf_nodes | None | |
| min_impurity_decrease | 0.0 | |
| bootstrap | True | |
| oob_score | False | |
| n_jobs | None | |
| random_state | 0 | |
| verbose | 0 | |
| warm_start | False | |
| class_weight | None | |
| ccp_alpha | 0.0 | |
| max_samples | None | |
| monotonic_cst | None |
Predicting a new result¶
In [11]:
print(classifier.predict(sc.transform([[30,87000]])))
[0]
Predicting the Test set results¶
In [12]:
y_pred = classifier.predict(X_test)
#print(np.concatenate((y_pred.reshape(len(y_pred),1), y_test.reshape(len(y_test),1)),1))
Making the Confusion Matrix¶
In [13]:
from sklearn.metrics import confusion_matrix, accuracy_score
cm = confusion_matrix(y_test, y_pred)
print(cm)
[[63 5] [ 4 28]]
In [14]:
accuracy_score(y_test, y_pred)
Out[14]:
0.91
Visualising the Training set results¶
In [15]:
colors = ['#FA8072', '#1E90FF']
In [16]:
from matplotlib.colors import ListedColormap
X_set, y_set = sc.inverse_transform(X_train), y_train
X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 10, stop = X_set[:, 0].max() + 10, step = 0.25),
np.arange(start = X_set[:, 1].min() - 1000, stop = X_set[:, 1].max() + 1000, step = 0.25))
plt.contourf(X1, X2, classifier.predict(sc.transform(np.array([X1.ravel(), X2.ravel()]).T)).reshape(X1.shape),
alpha = 0.75, cmap = ListedColormap(colors))
plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
for i, j in enumerate(np.unique(y_set)):
plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1], color = ListedColormap(colors)(i), label = j)
plt.title('Random Forest Classifier (Training set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()
Visualising the Test set results¶
In [17]:
from matplotlib.colors import ListedColormap
X_set, y_set = sc.inverse_transform(X_test), y_test
# Create a grid of points
X1, X2 = np.meshgrid(
np.arange(start=X_set[:, 0].min() - 1, stop=X_set[:, 0].max() + 1, step=0.25),
np.arange(start=X_set[:, 1].min() - 1, stop=X_set[:, 1].max() + 1, step=0.25)
)
# Predict for each point on the grid
Z = classifier.predict(sc.transform(np.array([X1.ravel(), X2.ravel()]).T)).reshape(X1.shape)
# Plot the decision boundary
plt.contourf(X1, X2, Z, alpha=0.75, cmap = ListedColormap(colors) )
plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
# Plot the test set points
for i, j in enumerate(np.unique(y_set)):
plt.scatter(
X_set[y_set == j, 0], X_set[y_set == j, 1],
color=colors[i], label=j
)
# Add titles and labels
plt.title('Random Forest Classifier (Test set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()
