In [1]:
import pandas
import numpy as np
from pandas.tools.plotting import scatter_matrix
import matplotlib.pyplot as plt
from sklearn import cross_validation
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
from sklearn.preprocessing import StandardScaler
#dataset.head(10)
zoo = r'C:\Users\priyu\Machine-Learning\zoo-animal-classification\zoo.csv'
#zoo_class = r'C:\Users\priyu\Machine-Learning\zoo-animal-classification\class.csv'
training_set = pandas.read_csv(zoo,index_col = False)
#zoo_class_set = pandas.read_csv(zoo_class, index_col = False)
zoo_data_df = training_set[['hair','feathers','eggs','milk','airborne','aquatic','predator','toothed','backbone','breathes','venomous','fins','legs','tail','domestic','catsize']]
zoo_target_df = training_set[['class_type']]
zoo_target = zoo_target_df.values
zoo_data = zoo_data_df.values
from sklearn import datasets
from sklearn.linear_model import LogisticRegression
#reading the iris dataset from the datasets package
iris = datasets.load_iris()
#print(iris.data.shape,iris.target.shape)
#implementing the methods of Logistic Regression
#m=LogisticRegression()
#model = LogisticRegression()
#m.fit(zoo_data,zoo_target)
#print(iris.target,iris.target_names,iris.feature_names,iris.DESCR)
# model.predict(iris.data)
#print(iris.target)
In [12]:
validation_size = 0.20
seed = 7
X_train, X_validation, Y_train, Y_validation = cross_validation.train_test_split(zoo_data, zoo_target, test_size=validation_size, random_state=seed)
In [19]:
#print(Y_train.shape)
y = Y_train.ravel()
Y_train = np.array(y).astype(int)
In [20]:
# Test options and evaluation metric
num_folds = 10
num_instances = len(X_train)
seed = 7
scoring = 'accuracy'
In [26]:
#Spot Check Algorithms
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()))
# evaluate each model in turn
results = []
names = []
for name, model in models:
kfold = cross_validation.KFold(n=num_instances, n_folds=num_folds, random_state=seed)
cv_results = cross_validation.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)
In [24]:
# model = LogisticRegression()
# results = []
# names = []
# kfold = cross_validation.KFold(n=num_instances, n_folds=num_folds, random_state=seed)
# cv_results = cross_validation.cross_val_score(model, X_train, Y_train, cv=kfold, scoring=scoring)
# results.append(cv_results)
# #names.append(name)
# msg = "%s: %f (%f)" % ('LR', cv_results.mean(), cv_results.std())
# print(msg)
In [27]:
# Make predictions on validation dataset
knn = KNeighborsClassifier()
knn.fit(X_train, Y_train)
predictions = knn.predict(X_validation)
print(accuracy_score(Y_validation, predictions))
print(confusion_matrix(Y_validation, predictions))
print(classification_report(Y_validation, predictions))