Edureka machine learning codes

In [5]:

import sys
print("python: {}".format(sys.version))
import scipy
print("scipy:  {}".format(scipy.__version__))
import numpy
print("numpy:  {}".format(numpy.__version__))

import matplotlib
print("mat:  {}".format(matplotlib.__version__))

import pandas
print("pandas:  {}".format(pandas.__version__))

import sklearn
print("sklearn:  {}".format(sklearn.__version__))

python: 3.7.4 (default, Aug  9 2019, 18:34:13) [MSC v.1915 64 bit (AMD64)]
scipy:  1.3.1
numpy:  1.16.5
mat:  3.1.1
pandas:  0.25.1
sklearn:  0.21.3

In [9]:

import pandas
from pandas.plotting import scatter_matrix
import matplotlib.pyplot as pit
from sklearn import model_selection
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC

In [10]:

url="https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data"
names=['sepal-length','sepal-width','petal-length','petal-width','class']
dataset = pandas.read_csv(url,names=names)

In [11]:

print(dataset.shape)

(150, 5)

In [13]:

print(dataset.head(30))

    sepal-length  sepal-width  petal-length  petal-width        class
0            5.1          3.5           1.4          0.2  Iris-setosa
1            4.9          3.0           1.4          0.2  Iris-setosa
2            4.7          3.2           1.3          0.2  Iris-setosa
3            4.6          3.1           1.5          0.2  Iris-setosa
4            5.0          3.6           1.4          0.2  Iris-setosa
5            5.4          3.9           1.7          0.4  Iris-setosa
6            4.6          3.4           1.4          0.3  Iris-setosa
7            5.0          3.4           1.5          0.2  Iris-setosa
8            4.4          2.9           1.4          0.2  Iris-setosa
9            4.9          3.1           1.5          0.1  Iris-setosa
10           5.4          3.7           1.5          0.2  Iris-setosa
11           4.8          3.4           1.6          0.2  Iris-setosa
12           4.8          3.0           1.4          0.1  Iris-setosa
13           4.3          3.0           1.1          0.1  Iris-setosa
14           5.8          4.0           1.2          0.2  Iris-setosa
15           5.7          4.4           1.5          0.4  Iris-setosa
16           5.4          3.9           1.3          0.4  Iris-setosa
17           5.1          3.5           1.4          0.3  Iris-setosa
18           5.7          3.8           1.7          0.3  Iris-setosa
19           5.1          3.8           1.5          0.3  Iris-setosa
20           5.4          3.4           1.7          0.2  Iris-setosa
21           5.1          3.7           1.5          0.4  Iris-setosa
22           4.6          3.6           1.0          0.2  Iris-setosa
23           5.1          3.3           1.7          0.5  Iris-setosa
24           4.8          3.4           1.9          0.2  Iris-setosa
25           5.0          3.0           1.6          0.2  Iris-setosa
26           5.0          3.4           1.6          0.4  Iris-setosa
27           5.2          3.5           1.5          0.2  Iris-setosa
28           5.2          3.4           1.4          0.2  Iris-setosa
29           4.7          3.2           1.6          0.2  Iris-setosa

In [14]:

print(dataset.describe())

       sepal-length  sepal-width  petal-length  petal-width
count    150.000000   150.000000    150.000000   150.000000
mean       5.843333     3.054000      3.758667     1.198667
std        0.828066     0.433594      1.764420     0.763161
min        4.300000     2.000000      1.000000     0.100000
25%        5.100000     2.800000      1.600000     0.300000
50%        5.800000     3.000000      4.350000     1.300000
75%        6.400000     3.300000      5.100000     1.800000
max        7.900000     4.400000      6.900000     2.500000

In [16]:

print(dataset.groupby('class').size())

class
Iris-setosa        50
Iris-versicolor    50
Iris-virginica     50
dtype: int64

In [23]:

dataset.plot(kind="box", subplots = True, layout=(2,2))
pit.show()

In [25]:

dataset.hist()
pit.show()

In [26]:

scatter_matrix(dataset)
pit.show()

In [28]:

array = dataset.values
X=array[:,0:4]
Y=array[:,4]
validation_size=0.20
seed=6
x_train, x_test, y_train, y_test= model_selection.train_test_split(X,Y,test_size=validation_size,random_state=seed)

In [42]:

seed=6
scoring ='accuracy'

In [48]:

models=[]
models.append(('LR', LogisticRegression()))
models.append(('LDA', LinearDiscriminantAnalysis()))
models.append(('Knn', KNeighborsClassifier()))
models.append(('CART', DecisionTreeClassifier()))
models.append(('NB', GaussianNB()))
models.append(('SVM', SVC()))
results=[]
names=[]
for name, model in models:
    kfold=model_selection.KFold(n_splits=13, random_state=seed)
    cv_results=model_selection.cross_val_score(model,x_train,y_train,cv=kfold,scoring=scoring)
    results.append(cv_results)
    names.append(name)
    msg= "%s: %f (%f)" % (name,cv_results.mean(), cv_results.std())
    print(msg)

LR: 0.941026 (0.054674)
LDA: 0.975214 (0.045323)
Knn: 0.958120 (0.068653)
CART: 0.941880 (0.053934)
NB: 0.966667 (0.050071)
SVM: 0.949573 (0.069814)