因為手上沒有iris.data資料，只能通過在sklearn中載入原始資料，並將其轉換為Dataframe格式

主要內容：資料分佈的視覺化（特徵之間分佈、特徵內部、分類精度、熱力圖） 

演算法：決策樹 隨機森林

import pandas as pd
from sklearn.datasets import load_iris
import numpy as np
# iris_data = pd.read_csv('iris.data')
iris = load_iris()
X, y = iris.data, iris.target

iris_data = pd.DataFrame(np.hstack((X, y.reshape(-1, 1))),index = range(X.shape[0]),columns=['sepal_length_cm','sepal_width_cm','petal_length_cm','petal_width_cm','class'] )

#如果拿到手的資料沒有 資料頭標籤 那可以通過下面這句話 新增標籤
# iris_data.columns = ['sepal_length_cm','sepal_width_cm','petal_length_cm','petal_width_cm','class'] 
# print(iris_data.head)

# from PIL import Image
import matplotlib.pyplot as plt
# img = Image.open('test.jpg')
# plt.imshow()
# plt.show()
# 
# #看一下資料的分佈規則 可以看數量 均值 方差 分位數等
print(iris_data.describe())
# 
# #強大的視覺化庫 可以檢視到不同特徵之間的關係 以及分佈
import seaborn as sb
sb.pairplot(iris_data.dropna(),hue = 'class')
 
plt.figure(figsize=(10,10))
for column_index,column in enumerate(iris_data.columns):
    if column == 'class':
        continue
    plt.subplot(2,2,column_index+1)
    sb.violinplot(x= 'class', y=column, data = iris_data)
plt.show()
 

輸出：

       sepal_length_cm  sepal_width_cm  petal_length_cm  petal_width_cm  \
count       150.000000      150.000000       150.000000      150.000000   
mean          5.843333        3.054000         3.758667        1.198667   
std           0.828066        0.433594         1.764420        0.763161   
min           4.300000        2.000000         1.000000        0.100000   
25%           5.100000        2.800000         1.600000        0.300000   
50%           5.800000        3.000000         4.350000        1.300000   
75%           6.400000        3.300000         5.100000        1.800000   
max           7.900000        4.400000         6.900000        2.500000   

            class  
count  150.000000  
mean     1.000000  
std      0.819232  
min      0.000000  
25%      0.000000  
50%      1.000000  
75%      2.000000  
max      2.000000  
 

利用seaborn和交叉驗證 對訓練精度進行視覺化

import pandas as pd
from sklearn.datasets import load_iris
import numpy as np
# iris_data = pd.read_csv('iris.data')
iris = load_iris()
X, y = iris.data, iris.target

iris_data = pd.DataFrame(np.hstack((X, y.reshape(-1, 1))),index = range(X.shape[0]),columns=['sepal_length_cm','sepal_width_cm','petal_length_cm','petal_width_cm','class'] )
import matplotlib.pyplot as plt
import seaborn as sb
from sklearn.cross_validation import train_test_split
all_inputs = iris_data[['sepal_length_cm','sepal_width_cm','petal_length_cm','petal_width_cm']].values #可以不用加values
all_classes = iris_data['class'].values #可以不用加values
training_inputs,testing_inputs,training_classes,testng_classes  = train_test_split(all_inputs,all_classes,train_size = 0.75,random_state = 1) #random_state 制定隨機數的種子

from sklearn.tree import DecisionTreeClassifier
decision_tree_classifier= DecisionTreeClassifier()
decision_tree_classifier.fit(training_inputs,training_classes)
print(decision_tree_classifier.score(testing_inputs,testng_classes)) #計算精度值
 
#對分類精度進行視覺化
from sklearn.cross_validation import cross_val_score
import numpy as np
decision_tree_classifier = DecisionTreeClassifier() # math_depth = 1
cv_scores = cross_val_score(decision_tree_classifier,all_inputs,all_classes,cv =10)
print(cv_scores)
sb.distplot(cv_scores) # kde = False
plt.title('Average score:{}'.format(np.mean(cv_scores)))
plt.show()
 

輸出：

0.9736842105263158
[1.         0.93333333 1.         0.93333333 0.93333333 0.86666667
 0.93333333 0.93333333 1.         1.        ]

通過GridSearchCV進行引數選擇 並將引數進行熱度圖視覺化，並通過最佳引數建立一個決策樹，通過graphviz將生成的dot檔案轉為pdf，但是本文沒有進行相關操作，以後有時間再試， 

隨後通過隨機森林進行分類的最佳引數選擇

import pandas as pd
from sklearn.datasets import load_iris
import numpy as np
# iris_data = pd.read_csv('iris.data')
iris = load_iris()
X, y = iris.data, iris.target

iris_data = pd.DataFrame(np.hstack((X, y.reshape(-1, 1))),index = range(X.shape[0]),columns=['sepal_length_cm','sepal_width_cm','petal_length_cm','petal_width_cm','class'] )
import matplotlib.pyplot as plt
import seaborn as sb
from sklearn.cross_validation import train_test_split
all_inputs = iris_data[['sepal_length_cm','sepal_width_cm','petal_length_cm','petal_width_cm']].values #可以不用加values
all_classes = iris_data['class'].values #可以不用加values
training_inputs,testing_inputs,training_classes,testng_classes  = train_test_split(all_inputs,all_classes,train_size = 0.75,random_state = 1) #random_state 制定隨機數的種子
from sklearn.tree import DecisionTreeClassifier
#通過GridSearchCV進行引數選擇
from sklearn.grid_search import GridSearchCV
from sklearn.cross_validation import StratifiedKFold
decision_tree_classifier = DecisionTreeClassifier()
parameter_grid = {'max_depth':[1,2,3,4,5],
                  'max_features':[1,2,3,4]}
cross_validation = StratifiedKFold(all_classes,n_folds=10)
grid_search = GridSearchCV(decision_tree_classifier,param_grid = parameter_grid,cv = cross_validation)
grid_search.fit(all_inputs, all_classes)
print('Best score:{}'.format(grid_search.best_score_))
print('Best parameter:{}'.format(grid_search.best_params_))
 
#將GridSearchCV選擇的引數進行熱度圖視覺化
grid_visualization = []
for grid_pair in grid_search.grid_scores_:
    grid_visualization.append(grid_pair.mean_validation_score)
grid_visualization = np.array(grid_visualization)
grid_visualization.shape = (5,4)
sb.heatmap(grid_visualization,cmap='Blues')
plt.xticks(np.arange(4)+0.5,grid_search.param_grid['max_features'])
plt.yticks(np.arange(5)+0.5,grid_search.param_grid['max_depth'][::-1])
plt.xlabel('max_features')
plt.ylabel('max_depth')
#通過上面的引數選擇 將最好的引數建立一個決策樹
decision_tree_classifier = grid_search.best_estimator_
import sklearn.tree as tree
from sklearn.externals.six import StringIO
with open('iris_dtc.dot','w') as out_file:
    out_file = tree.export_graphviz(decision_tree_classifier,out_file=out_file)
    #可以通過下載graphviz軟體將dot檔案轉換為 pdf檔案 http://www.graphviz.org/
 
#通過隨機森林選擇最佳引數分類
from sklearn.ensemble import RandomForestClassifier
random_forest_classifier = RandomForestClassifier()
parameter_grid = {'n_estimators':[5,10,25,50],
                  'criterion':['gini','entropy'],
                  'max_features':[1,2,3,4],
                  'warm_start':[True,False]}
cross_validation = StratifiedKFold(all_classes,n_folds = 10)
grid_search = GridSearchCV(random_forest_classifier,param_grid=parameter_grid,cv = cross_validation)
grid_search.fit(all_inputs,all_classes)
print('Best score:{}'.format(grid_search.best_score_))
print('Best parameter:{}'.format(grid_search.best_params_))
print('Best_estimator:{}'.format(grid_search.best_estimator_))
plt.show()

輸出：

D:\F\Anaconda3\lib\site-packages\sklearn\cross_validation.py:44: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. Also note that the interface of the new CV iterators are different from that of this module. This module will be removed in 0.20.
  "This module will be removed in 0.20.", DeprecationWarning)
D:\F\Anaconda3\lib\site-packages\sklearn\grid_search.py:43: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. This module will be removed in 0.20.
  DeprecationWarning)
Best score:0.9666666666666667
Best parameter:{'max_depth': 3, 'max_features': 2}
Best score:0.9733333333333334
Best parameter:{'criterion': 'gini', 'max_features': 3, 'n_estimators': 10, 'warm_start': True}
Best_estimator:RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',
            max_depth=None, max_features=3, max_leaf_nodes=None,
            min_impurity_split=1e-07, min_samples_leaf=1,
            min_samples_split=2, min_weight_fraction_leaf=0.0,
            n_estimators=10, n_jobs=1, oob_score=False, random_state=None,
            verbose=0, warm_start=True)