1_summarize_dataset.py

# 1. Load Libraries
from pandas import read_csv
from pandas.plotting import scatter_matrix
from matplotlib import pyplot
from sklearn.model_selection import train_test_split
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import StratifiedKFold
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

# Load the Data
names=['sepal-length', 'sepal-width', 'petal-length', 'petal-width', 'class']
dataset = read_csv('iris.csv', names=names)

# shape
print(dataset.shape)

#head
print(dataset.head(20))

#description
print(dataset.describe())

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