تولید داده‌های تست برای یادگیری ماشین

# Import necessary libraries
from sklearn.datasets import make_circles
import matplotlib.pyplot as plt

# Generate 2d classification dataset 
X, y = make_circles(n_samples=200, shuffle=True, 
					noise=0.1, random_state=42)
# Plot the generated datasets
plt.scatter(X[:, 0], X[:, 1], c=y)
plt.show()

#import the necessary libraries
from sklearn.datasets import make_moons
import matplotlib.pyplot as plt
# generate 2d classification dataset
X, y = make_moons(n_samples=500, shuffle=True,
				noise=0.15, random_state=42)
# Plot the generated datasets
plt.scatter(X[:, 0], X[:, 1], c=y)
plt.show()

#import the necessary libraries
from sklearn.datasets import make_blobs
import matplotlib.pyplot as plt

# Generate 2d classification dataset
X, y = make_blobs(n_samples=500, centers=3, n_features=2, random_state=23)

# Plot the generated datasets
plt.scatter(X[:, 0], X[:, 1], c=y)
plt.show()

from sklearn.datasets import make_classification
import matplotlib.pyplot as plt

# generate 2d classification dataset
X, y = make_classification(n_samples = 100, 
						n_features=2,
						n_redundant=0,
						n_informative=2,
						n_repeated=0,
						n_classes =3,
						n_clusters_per_class=1)

# Plot the generated datasets
plt.scatter(X[:, 0], X[:, 1], c=y)
plt.show()

# Import necessary libraries
from sklearn.datasets import make_multilabel_classification
import pandas as pd
import matplotlib.pyplot as plt

# Generate 2d classification dataset 
X, y = make_multilabel_classification(n_samples=500, n_features=2, 
									n_classes=2, n_labels=2,
									allow_unlabeled=True,
									random_state=23)
# create pandas dataframe from generated dataset
df = pd.concat([pd.DataFrame(X, columns=['X1', 'X2']), 
				pd.DataFrame(y, columns=['Label1', 'Label2'])],
			axis=1)
display(df.head())

# Plot the generated datasets
plt.scatter(df['X1'], df['X2'], c=df['Label1'])
plt.show()

# Import necessary libraries
from sklearn.datasets import make_regression
import matplotlib.pyplot as plt
# Generate 1d Regression dataset 
X, y = make_regression(n_samples = 50, n_features=1,noise=20, random_state=23)
# Plot the generated datasets
plt.scatter(X, y)
plt.show()

# Import necessary libraries
from sklearn.datasets import make_sparse_uncorrelated
import matplotlib.pyplot as plt
# Generate 1d Regression dataset 
X, y = make_sparse_uncorrelated(n_samples = 100, n_features=4, random_state=23)
# Plot the generated datasets
plt.figure(figsize=(12,10))
for i in range(4):
	plt.subplot(2,2, i+1)
	plt.scatter(X[:,i], y)
	plt.xlabel('X'+str(i+1))
	plt.ylabel('Y')
plt.show()

# Import necessary libraries
from sklearn.datasets import make_friedman2
import matplotlib.pyplot as plt
# Generate 1d Regression dataset 
X, y = make_friedman2(n_samples = 100, random_state=23)
# Plot the generated datasets
plt.figure(figsize=(12,10))
for i in range(4):
	plt.subplot(2,2, i+1)
	plt.scatter(X[:,i], y)
	plt.xlabel('X'+str(i+1))
	plt.ylabel('Y')
plt.show()

# importing libraries
from sklearn.datasets import make_blobs

# matplotlib for plotting
from matplotlib import pyplot as plt 
from matplotlib import style

# Creating Test DataSets using sklearn.datasets.make_blobs
from sklearn.datasets import make_blobs
from matplotlib import pyplot as plt 
from matplotlib import style

style.use("fivethirtyeight")

X, y = make_blobs(n_samples = 100, centers = 3, 
			cluster_std = 1, n_features = 2)

plt.scatter(X[:, 0], X[:, 1], s = 40, color = 'g')
plt.xlabel("X")
plt.ylabel("Y")

plt.show()
plt.clf()

# Creating Test DataSets using sklearn.datasets.make_moon
from sklearn.datasets import make_moons
from matplotlib import pyplot as plt 
from matplotlib import style

X, y = make_moons(n_samples = 1000, noise = 0.1)
plt.scatter(X[:, 0], X[:, 1], s = 40, color ='g')
plt.xlabel("X")
plt.ylabel("Y")

plt.show()
plt.clf()

# Creating Test DataSets using sklearn.datasets.make_circles
from sklearn.datasets import make_circles
from matplotlib import pyplot as plt 
from matplotlib import style

style.use("fivethirtyeight")

X, y = make_circles(n_samples = 100, noise = 0.02)
plt.scatter(X[:, 0], X[:, 1], s = 40, color ='g')
plt.xlabel("X")
plt.ylabel("Y")

plt.show()
plt.clf()