分类标签归档：sklearn
KNN最邻近分类在距离空间里，如果一个样本的最接近的k个邻居里，绝大多数属于某个类别，则该样本也属于这个类别
案例一：电影数据分类# 案例一：电影数据分类
from sklearn import neighbors # 导入KNN分类模块
import warnings
warnings.filterwarnings('ignore')
# 不发出警告
data = pd.DataFrame({'name':['北京遇上西雅图','喜欢你','疯狂动物城','战狼2','力王','敢死队'],
import pandas as pd
names=['preg','plas','pres','skin','test','mass','pedi','age','class']
df = pd.read_csv("./pima-indians-diabetes.csv",names=names)
df.head()
【0】Pregnancies：怀孕次数
【1】Glucose：葡萄糖
【2】BloodPresfrom sklearn.feature_selection import SelectKBest
from sklearn.datasets import load_iris
iris = load_iris()
X,y = iris.data,iris.target
X[:5,:]
X_new = SelectKBest(k=2).fit_transform(X,y)
X_new[:5,:] # 计算相关系数后 发现这两列和y值相关度最高
结果：
X_new[:5,:] # 计算相关系数后 发现这两列和y值相关度最高
1
# 工具库
import pandas as pd
# 泰坦尼克数据集
df_train = pd.read_csv('titanic.csv')
# 了解一下数据集
df_train.head()
df_train.shape # 查看维度df_train.info() # 数据集信息import pandas as pd
from sklearn import preprocessing
from sklearn import tree
from sklearn.datasets import load_boston # 波士顿房价
boston_house = load_boston()boston_feature_name = boston_house.feature_names
boston_features = boston_house.data
boston_target = boston_house.targetboston_featuimport pandas as pd
from sklearn import preprocessing
from sklearn import tree
from sklearn.datasets import load_iris # 花瓣种类
# 加载数据
iris = load_iris()
dir(iris) # iris包含的内容有哪些 如果不懂某些方法 可用 help(iris)
['DESCR', 'data', 'feature_names', 'filename', 'target', 'target_names']
iris_feature_names = ir# 用于数据处理和分析的工具包
import pandas as pd
# 数据处理/特征工程的包
from sklearn import preprocessing
# 决策树建模包
from sklearn import tree
adult_data = pd.read_csv('./DecisionTree.csv')
# 读取前5行
adult_data.head(5)
adult_data.info() # 读入数据的信息<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1000 e#conding=utf-8
import pandas as pd
import numpy as np
import matplotlib as mpl
import matplotlib.pyplot as plt
from scipy.optimize import minimize
from sklearn.preprocessing import PolynomialFeatures
# pandas 基础设置
pd.set_option('display.notebook_repr_html',False)
pd.set_option('disp#conding=utf-8
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.linear_model import LinearRegression
from mpl_toolkits.mplot3d import axes3d
# pandas 基础设置
pd.set_option('display.notebook_repr_html',False)
pd.set_option('display.max_columns',Non