from sklearn import preprocessing
label_encoder = preprocessing.LabelEncoder()
data['Gender']=label_encoder.fit_transform(data['Gender'])
data['Gender']=label_encoder.fit_transform(data['Gender'])
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
X = data.drop(columns = ['Profession'],axis=1)
y = data['Profession']
x_train,y_test,t_train,t_test = train_test_split(X,y,test_size=0.3)
model = tree.DecisionTreeClassifier()
model = model.fit(x_train,t_train)
predicted_value = model.predict(y_test)
accuracy = accuracy_score(t_test,predicted_value)
importing scikit learn with make_blobs
from sklearn.datasets.samples_generator import make_blobs
creating datasets X containing n_samples
Y containing two classes
X, Y = make_blobs(n_samples=500, centers=2,
random_state=0, cluster_std=0.40)
import matplotlib.pyplot as plt
plotting scatters
plt.scatter(X[:, 0], X[:, 1], c=Y, s=50, cmap='spring');
plt.show()
importing required libraries
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
reading csv file and extracting class column to y.
x = pd.read_csv("C:...\cancer.csv")
a = np.array(x)
y = a[:,30] # classes having 0 and 1
extracting two features
x = np.column_stack((x.malignant,x.benign))
569 samples and 2 features
x.shape
print (x),(y)
clf.predict([[120, 990]])
clf.predict([[85, 550]])
https://www.geeksforgeeks.org/classifying-data-using-support-vector-machinessvms-in-python/