import numpy as np
import pandas as pd
import matplotlib.pyplot as pl
from sklearn import linear_model
df = pd.read_csv(“dataset1.csv”)
df
Output:
df.shape
Output: (5, 2)
%matplotlib inline
pl.xlabel(‘Area in square feet’)
pl.ylabel(‘Price in Rupees’)
pl.scatter(df.area,df.price, color=‘b’, marker=‘s’)
reg = linear_model.LinearRegression()
reg.fit(df[[‘area’]],df.price)
Output: LinearRegression()
reg.coef_ #coef is m (slope)
Output: array([135.78767123])
reg.predict([[3300]])
Output: array([628715.75342466])
reg.intercept_ #intercept is b
Output: 180616.43835616432
# y = m * x + b
135.78767123 * 3300 + 180616.43835616432
Output: 628715.7534151643
import numpy as np
import pandas as pd
from matplotlib import pyplot as pl
df1 = pd.read_csv(“loan.csv”)
df1.head()
pl.scatter(df1.age,df1.bought_loan, marker=‘d’, color=‘b’)
Output:
from sklearn.model_selection import train_test_split
x_train, x_test,y_train,y_test = train_test_split(df1[[‘age’]], df1.bought_loan, train_size=0.9, shuffle=False)
x_test
Output:
from sklearn.linear_model import LogisticRegression
logreg = LogisticRegression()
logreg.fit(x_train,y_train)
Output: LogisticRegression()
logreg.predict(x_test)
Output: array([0, 1, 1], dtype=int64)
import numpy as np
import pandas as pd
ds = pd.read_csv(“iris.csv”)
ds
Output:
ds.iloc[:,1:5]
Output:
x = ds.iloc[:, 1:5].values
from sklearn.preprocessing import LabelEncoder #0 and nclass-1
lblenc_y = LabelEncoder()
y = lblenc_y.fit_transform(y)
y
from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(x,y,test_size=0.2)
from sklearn.neighbors import KNeighborsClassifier
knn_model = KNeighborsClassifier(n_neighbors=5)
knn_model.fit(x_train, y_train)
Output: KNeighborsClassifier()
y_predict = knn_model.predict(x_test)
from sklearn.metrics import confusion_matrix, classification_report
print(confusion_matrix(y_test,y_predict))
Output:
[[13 0 0]
[0 7 2]
[0 0 8]]
#accuracy
print(28/30)
Output: 0.9333333333333333
print(classification_report(y_test, y_predict))