In [2]:
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
In [5]:
zoo_class_set.plot(kind='box', subplots=True, layout=(2,2), sharex=False, sharey=False)
plt.show()
In [ ]:
#correlation matrix plot
In [6]:
scatter_matrix(zoo_class_set)
plt.show()
In [11]:
zoo_class_set.plot(kind='density', subplots=False, layout=(3,3), sharex=False)
plt.show()
In [12]:
zoo_class_set.hist()
plt.show()
In [23]:
correlations = training_set.corr()
names = ['hair','feathers','eggs','milk','airborne','aquatic','predator','toothed','backbone','breathes','venomous','fins','legs','tail','domestic','catsize']
# plot correlation matrix
fig = plt.figure()
ax = fig.add_subplot(111)
cax = ax.matshow(correlations, vmin=-1, vmax=1)
fig.colorbar(cax)
ticks = np.arange(0,15,1)
ax.set_xticks(ticks)
ax.set_yticks(ticks)
ax.set_xticklabels(names)
ax.set_yticklabels(names)
plt.show()