forked from Avik-Jain/100-Days-Of-ML-Code
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
1 changed file
with
81 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,81 @@ | ||
# Decision Tree Classification | ||
|
||
### Importing the libraries | ||
```python | ||
import numpy as np | ||
import matplotlib.pyplot as plt | ||
import pandas as pd | ||
``` | ||
|
||
### Importing the dataset | ||
```python | ||
dataset = pd.read_csv('Social_Network_Ads.csv') | ||
X = dataset.iloc[:, [2, 3]].values | ||
y = dataset.iloc[:, 4].values | ||
``` | ||
### Splitting the dataset into the Training set and Test set | ||
```python | ||
from sklearn.cross_validation import train_test_split | ||
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 0) | ||
``` | ||
|
||
### Feature Scaling | ||
```python | ||
from sklearn.preprocessing import StandardScaler | ||
sc = StandardScaler() | ||
X_train = sc.fit_transform(X_train) | ||
X_test = sc.transform(X_test) | ||
``` | ||
### Fitting Decision Tree Classification to the Training set | ||
```python | ||
from sklearn.tree import DecisionTreeClassifier | ||
classifier = DecisionTreeClassifier(criterion = 'entropy', random_state = 0) | ||
classifier.fit(X_train, y_train) | ||
``` | ||
### Predicting the Test set results | ||
```python | ||
y_pred = classifier.predict(X_test) | ||
``` | ||
### Making the Confusion Matrix | ||
```python | ||
from sklearn.metrics import confusion_matrix | ||
cm = confusion_matrix(y_test, y_pred) | ||
``` | ||
### Visualising the Training set results | ||
```python | ||
from matplotlib.colors import ListedColormap | ||
X_set, y_set = X_train, y_train | ||
X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01), | ||
np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01)) | ||
plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape), | ||
alpha = 0.75, cmap = ListedColormap(('red', 'green'))) | ||
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], | ||
c = ListedColormap(('red', 'green'))(i), label = j) | ||
plt.title('Decision Tree Classification (Training set)') | ||
plt.xlabel('Age') | ||
plt.ylabel('Estimated Salary') | ||
plt.legend() | ||
plt.show() | ||
``` | ||
### Visualising the Test set results | ||
```python | ||
from matplotlib.colors import ListedColormap | ||
X_set, y_set = X_test, y_test | ||
X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01), | ||
np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01)) | ||
plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape), | ||
alpha = 0.75, cmap = ListedColormap(('red', 'green'))) | ||
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], | ||
c = ListedColormap(('red', 'green'))(i), label = j) | ||
plt.title('Decision Tree Classification (Test set)') | ||
plt.xlabel('Age') | ||
plt.ylabel('Estimated Salary') | ||
plt.legend() | ||
plt.show() | ||
``` |