#!/usr/bin/env python
# coding: utf-8

# In[1]:


import pandas as pd
from sklearn import datasets, model_selection, svm, metrics


# In[2]:


# http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_iris.html
# http://scikit-learn.org/stable/auto_examples/datasets/plot_iris_dataset.html
iris = datasets.load_iris()


# In[3]:


print(type(iris))
print(iris.keys())


# In[4]:


iris_data = pd.DataFrame(data=iris.data, columns=iris.feature_names)
print(iris_data.head())


# In[5]:


iris_label = pd.Series(data=iris.target)
print(iris_label.head())


# In[6]:


print(len(iris_data))


# In[7]:


# http://scikit-learn.org/stable/modules/generated/sklearn.model_selection.train_test_split.html
data_train, data_test, label_train, label_test = model_selection.train_test_split(iris_data, iris_label)


# In[8]:


print(data_train.head())


# In[9]:


print(label_train.head())


# In[10]:


# default value of test_size = 0.25
print(len(data_train), len(data_test))


# In[11]:


clf = svm.SVC()
clf.fit(data_train, label_train)
pre = clf.predict(data_test)


# In[12]:


print(type(pre))
print(pre)


# In[13]:


# http://scikit-learn.org/stable/modules/generated/sklearn.metrics.accuracy_score.html
ac_score = metrics.accuracy_score(label_test, pre)


# In[14]:


print(ac_score)


# In[15]:


scores = model_selection.cross_val_score(clf, iris_data, iris_label, cv=3)
print(scores)
print(scores.mean())