algorithm/Python
1
0
Fork 0
mirror of https://github.com/TheAlgorithms/Python.git synced 2025-07-19 19:03:02 +08:00
Code Issues Packages Projects Releases Wiki Activity

psf/black code formatting (#1277)

Browse Source
This commit is contained in:
William Zhang
2019-10-05 01:14:13 -04:00
committed by Christian Clauss
parent 07f04a2e55
commit 9eac17a408
291 changed files with 6014 additions and 4571 deletions
Download Patch File Download Diff File Expand all files Collapse all files

74
machine_learning/random_forest_classification/random_forest_classification.py
View File

@ -8,23 +8,30 @@ import pandas as pd
# Importing the dataset
script_dir = os.path.dirname(os.path.realpath(__file__))
dataset = pd.read_csv(os.path.join(script_dir, 'Social_Network_Ads.csv'))
dataset = pd.read_csv(os.path.join(script_dir, "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
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)
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.25, random_state=0
)
# Feature Scaling
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
# Fitting Random Forest Classification to the Training set
from sklearn.ensemble import RandomForestClassifier
classifier = RandomForestClassifier(n_estimators = 10, criterion = 'entropy', random_state = 0)
classifier = RandomForestClassifier(
n_estimators=10, criterion="entropy", random_state=0
)
classifier.fit(X_train, y_train)
# Predicting the Test set results
@ -32,40 +39,65 @@ y_pred = classifier.predict(X_test)
# Making the Confusion Matrix
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)
# Visualising the Training set results
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')))
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('Random Forest Classification (Training set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.scatter(
X_set[y_set == j, 0],
X_set[y_set == j, 1],
c=ListedColormap(("red", "green"))(i),
label=j,
)
plt.title("Random Forest Classification (Training set)")
plt.xlabel("Age")
plt.ylabel("Estimated Salary")
plt.legend()
plt.show()
# Visualising the Test set results
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')))
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('Random Forest Classification (Test set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.scatter(
X_set[y_set == j, 0],
X_set[y_set == j, 1],
c=ListedColormap(("red", "green"))(i),
label=j,
)
plt.title("Random Forest Classification (Test set)")
plt.xlabel("Age")
plt.ylabel("Estimated Salary")
plt.legend()
plt.show()