machine learning (code with harry and other)
In [1]:
from IPython.display import Image
from IPython.core.display import HTML
from IPython.display import IFrame
In [4]:
Image(url= "https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhF-63Pf6FYdFZq7LzjuEg6UCuvKj0-gy9XgcjGpKtta3x0VTh84tabWwkmW96AQEQlVzI7o0EUlW60Nec-cq0bc8jicwFznKEX7XAP501GGZ3_MpWUL758w6VqcWWMy9hzyp-YWz6ddD4/s640/Screenshot+%25285555%2529.png")
Out[4]:
In [7]:
import matplotlib.pyplot as plt
import numpy as np
from sklearn import datasets,linear_model
from sklearn.metrics import mean_squared_error
In [8]:
diabetes=datasets.load_diabetes()
In [24]:
diabetes
Out[24]:
In [51]:
diabetes_x=diabetes.data[:,np.newaxis,2]
# diabetes_x=diabetes.data
In [68]:
diabetes_x_train=diabetes_x[:-30] # last ke 60 ko chhodkar(skip kar)
diabetes_x_test=diabetes_x[-30:] # last ke 40
In [23]:
diabetes_x_train
Out[23]:
In [16]:
# temp example for slicing (not part of this program)
lst=[1,2,3,4,5,6,7,8,9]
print(lst[:-4])
print(lst[-4:])
In [66]:
diabetes_y_train=diabetes_x[:-30]
diabetes_y_test=diabetes_x[-30:]
In [65]:
model=linear_model.LinearRegression()
model
Out[65]:
In [54]:
model.fit(diabetes_x_train,diabetes_y_train)
Out[54]:
In [21]:
diabetes_y_predicted=model.predict(diabetes_x_test)
diabetes_y_predicted
Out[21]:
In [25]:
print("mean square error is : ",mean_squared_error(diabetes_y_test,diabetes_y_predicted))
In [29]:
print("weights : ",model.coef_)
In [47]:
from sklearn.datasets import load_boston
In [32]:
boston=load_boston()
model.fit(boston.data, boston.target)
print("weights : ",model.coef_)
In [48]:
print("intercept : ",model.intercept_)
In [71]:
plt.scatter(diabetes_x_test,diabetes_y_test)
plt.show()
In [42]:
plt.plot(diabetes_x_test,diabetes_y_predicted)
Out[42]:
code in one cell¶
In [72]:
import matplotlib.pyplot as plt
import numpy as np
from sklearn import datasets, linear_model
from sklearn.metrics import mean_squared_error
from sklearn.datasets import load_boston
diabetes = datasets.load_diabetes()
diabetes_x = diabetes.data[:, np.newaxis, 2]
# diabetes_x=diabetes.data
diabetes_x_train = diabetes_x[:-30] # last ke 60 ko chhodkar(skip kar)
diabetes_x_test = diabetes_x[-30:] # last ke 40
diabetes_y_train = diabetes_x[:-30]
diabetes_y_test = diabetes_x[-30:]
model = linear_model.LinearRegression()
model.fit(diabetes_x_train, diabetes_y_train)
diabetes_y_predicted = model.predict(diabetes_x_test)
print("mean square error is : ", mean_squared_error(
diabetes_y_test, diabetes_y_predicted))
boston = load_boston()
model.fit(boston.data, boston.target)
print("weights : ", model.coef_)
print("intercept : ", model.intercept_)
plt.scatter(diabetes_x_test, diabetes_y_test)
plt.show()
plt.plot(diabetes_x_test, diabetes_y_predicted)
plt.show()
In [ ]:
In [1]:
from IPython.display import Image
from IPython.core.display import HTML
from IPython.display import IFrame
Linear Regression¶
In [4]:
Image(url= "https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhF-63Pf6FYdFZq7LzjuEg6UCuvKj0-gy9XgcjGpKtta3x0VTh84tabWwkmW96AQEQlVzI7o0EUlW60Nec-cq0bc8jicwFznKEX7XAP501GGZ3_MpWUL758w6VqcWWMy9hzyp-YWz6ddD4/s640/Screenshot+%25285555%2529.png")
Out[4]:
In [7]:
import matplotlib.pyplot as plt
import numpy as np
from sklearn import datasets,linear_model
from sklearn.metrics import mean_squared_error
In [8]:
diabetes=datasets.load_diabetes()
In [24]:
diabetes
Out[24]:
In [51]:
diabetes_x=diabetes.data[:,np.newaxis,2]
# diabetes_x=diabetes.data
In [68]:
diabetes_x_train=diabetes_x[:-30] # last ke 60 ko chhodkar(skip kar)
diabetes_x_test=diabetes_x[-30:] # last ke 40
In [23]:
diabetes_x_train
Out[23]:
In [16]:
# temp example for slicing (not part of this program)
lst=[1,2,3,4,5,6,7,8,9]
print(lst[:-4])
print(lst[-4:])
In [66]:
diabetes_y_train=diabetes_x[:-30]
diabetes_y_test=diabetes_x[-30:]
In [65]:
model=linear_model.LinearRegression()
model
Out[65]:
In [54]:
model.fit(diabetes_x_train,diabetes_y_train)
Out[54]:
In [21]:
diabetes_y_predicted=model.predict(diabetes_x_test)
diabetes_y_predicted
Out[21]:
In [25]:
print("mean square error is : ",mean_squared_error(diabetes_y_test,diabetes_y_predicted))
In [29]:
print("weights : ",model.coef_)
In [47]:
from sklearn.datasets import load_boston
In [32]:
boston=load_boston()
model.fit(boston.data, boston.target)
print("weights : ",model.coef_)
In [48]:
print("intercept : ",model.intercept_)
In [71]:
plt.scatter(diabetes_x_test,diabetes_y_test)
plt.show()
In [42]:
plt.plot(diabetes_x_test,diabetes_y_predicted)
Out[42]:
code in one cell (Linear Regression)¶
In [72]:
import matplotlib.pyplot as plt
import numpy as np
from sklearn import datasets, linear_model
from sklearn.metrics import mean_squared_error
from sklearn.datasets import load_boston
diabetes = datasets.load_diabetes()
diabetes_x = diabetes.data[:, np.newaxis, 2]
# diabetes_x=diabetes.data
diabetes_x_train = diabetes_x[:-30] # last ke 60 ko chhodkar(skip kar)
diabetes_x_test = diabetes_x[-30:] # last ke 40
diabetes_y_train = diabetes_x[:-30]
diabetes_y_test = diabetes_x[-30:]
model = linear_model.LinearRegression()
model.fit(diabetes_x_train, diabetes_y_train)
diabetes_y_predicted = model.predict(diabetes_x_test)
print("mean square error is : ", mean_squared_error(
diabetes_y_test, diabetes_y_predicted))
boston = load_boston()
model.fit(boston.data, boston.target)
print("weights : ", model.coef_)
print("intercept : ", model.intercept_)
plt.scatter(diabetes_x_test, diabetes_y_test)
plt.show()
plt.plot(diabetes_x_test, diabetes_y_predicted)
plt.show()
K Nearest Neighbor Classification¶
In [2]:
from sklearn import datasets
iris=datasets.load_iris()
In [3]:
print(iris.DESCR)
In [6]:
feature=iris.data
label=iris.target
In [7]:
print(feature[0]," ",label[0])
In [15]:
print(feature[64]," ",label[64])
In [16]:
from sklearn.neighbors import KNeighborsClassifier
In [18]:
clf=KNeighborsClassifier()
In [19]:
clf.fit(feature,label)
Out[19]:
In [23]:
preds=clf.predict([[1,1,1,1]])
preds
Out[23]:
In [25]:
preds=clf.predict([[31,1,1,1]])
preds
Out[25]:
code in one cell (K Nearest Neighbor Classification)¶
In [29]:
from sklearn import datasets
from sklearn.neighbors import KNeighborsClassifier
#Loading datasets
iris=datasets.load_iris()
#printing description and features
#print(iris.DESCR)
feature=iris.data
label=iris.target
print(feature[0]," ",label[0])
print(feature[64]," ",label[64])
#Training the classifier
clf=KNeighborsClassifier()
clf.fit(feature,label)
preds1=clf.predict([[1,1,1,1]])
print("prediction1 ",preds1)
preds2=clf.predict([[31,1,1,1]])
print("prediction2 ",preds2)
In [ ]:
Comments
Post a Comment