iad

# coding: utf-8


# In[5]:


print('Python: {}'.format(sys.version))


# In[6]:


# Python version
import sys
print('Python: {}'.format(sys.version))
# scipy
import scipy
print('scipy: {}'.format(scipy.__version__))
# numpy
import numpy
print('numpy: {}'.format(numpy.__version__))
# matplotlib
import matplotlib
print('matplotlib: {}'.format(matplotlib.__version__))
# pandas
import pandas
print('pandas: {}'.format(pandas.__version__))
# scikit-learn
import sklearn
print('sklearn: {}'.format(sklearn.__version__))


# In[8]:


# Load libraries
import pandas
from pandas.plotting import scatter_matrix
import matplotlib.pyplot as plt
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[9]:


# Load dataset
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[10]:


# shape
print(dataset.shape)


# In[11]:


# head
print(dataset.head(20))


# In[12]:


# descriptions
print(dataset.describe())


# In[13]:


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


# In[14]:


# box and whisker plots
dataset.plot(kind='box', subplots=True, layout=(2,2), sharex=False, sharey=False)
plt.show()


# In[21]:


# histograms
dataset.hist()
plt.show()


# In[37]:


import matplotlib.pyplot as plt
plt.rcParams["figure.figsize"] = (30,30)

# scatter plot matrix
scatter_matrix(dataset)
plt.show()