机器学习初步

机器学习初步

import pandas as pd
from sklearn.tree import DecisionTreeClassifier
​
music_data =pd.read_csv('music.csv')
X = music_data.drop(columns=['genre'])
y = music_data['genre']
​
model=DecisionTreeClassifier()
model.fit(X,y)
predictions=model.predict([[21,1],[22,0]])
predictions
#
array(['HipHop', 'Dance'], dtype=object)

Calculating the Accuracy

import pandas as pd
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
​
music_data =pd.read_csv('music.csv')
X = music_data.drop(columns=['genre'])
y = music_data['genre']
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2)
​
model=DecisionTreeClassifier()#create a model
model.fit(X_train,y_train)#train it
predictions=model.predict(X_test)
score=accuracy_score(y_test,predictions)
score
#每次运行都可能会出现0-1之间不同的结果。
​

Persisting Models

import pandas as pd
from sklearn.tree import DecisionTreeClassifier
import joblib
​
#music_data =pd.read_csv('music.csv')
#X = music_data.drop(columns=['genre'])
#y = music_data['genre']
​
#model=DecisionTreeClassifier()
#model.fit(X,y)
​
model=joblib.load('music_recommdender.joblib')
predictions=model.predict([[21,1]])#数组里面的一个元素
predictions
#
array(['HipHop'], dtype=object)

Visualizing a Decision Tree

import pandas as pd
from sklearn.tree import DecisionTreeClassifier
from sklearn import tree
music_data =pd.read_csv('music.csv')
X = music_data.drop(columns=['genre'])
y = music_data['genre']
​
model=DecisionTreeClassifier()
model.fit(X,y)
​
tree.export_graphviz(model,out_file='music-recommender.dot',
                     feature_names=['age','gender'],#以性别和年龄作为特征
                     class_names=sorted(y.unique()),#将类名设置为唯一的类型列表，为了显示每个音乐的种类
                     label='all',#每个结点有可以读的标签
                     rounded=True,#有圆角
                     filled=True#每个盒子，每个节点都有颜色)
​

将‘music-recommender.dot'拖拽到vscode中，下载相应的插件然后preview