gemoumou的python学习实记

SVM算法-线性分类 import numpy as np import matplotlib.pyplot as plt from sklearn import svm # 创建40个点 x_data = np.r_[np.random.randn(20, 2) - [2, 2], np.random.randn(20, 2) + [2, 2]] y_data = [0]*20 +[1]*20 plt.scatter(x_data[:,0],x_data[:,1],c=y_data) plt.show

PCA算法-手写数字降维可视化 from sklearn.neural_network import MLPClassifier from sklearn.datasets import load_digits from sklearn.model_selection import train_test_split from sklearn.metrics import classification_report,confusion_matrix import numpy as np import matp

KMEANS算法-NBA球队实力聚类分析 from sklearn.cluster import KMeans import numpy as np import matplotlib.pyplot as plt import pandas as pd from sklearn.preprocessing import MinMaxScaler data = pd.read_csv('nba.csv') data.head() minmax_scaler = MinMaxScaler() # 标准化

贝叶斯-新闻分类 from sklearn.datasets import fetch_20newsgroups from sklearn.model_selection import train_test_split news = fetch_20newsgroups(subset='all') print(news.target_names) print(len(news.data)) print(len(news.target)) print(len(news.target_names))

集成学习-泰坦尼克号船员获救预测 import pandas titanic = pandas.read_csv("titanic_train.csv") titanic # 空余的age填充整体age的中值 titanic["Age"] = titanic["Age"].fillna(titanic["Age"].median()) print(titanic.describe()) print(titanic["Sex"].unique()) # 把male变成0，把female变成1

机器学习实战-决策树-叶子分类 import numpy as np import pandas as pd import seaborn as sns import matplotlib.pyplot as plt from sklearn.preprocessing import LabelEncoder from sklearn.model_selection import train_test_split from sklearn.tree import DecisionTreeClassifi

# pip install scikit-learn --upgrade from sklearn.neural_network import MLPClassifier from sklearn.datasets import load_digits from sklearn.model_selection import train_test_split from sklearn.preprocessing import StandardScaler from sklearn.metrics import

# 导入算法包以及数据集 from sklearn import neighbors from sklearn import datasets from sklearn.model_selection import train_test_split from sklearn.metrics import classification_report import random # 载入数据 iris = datasets.load_iris() print(iris) # 打乱数据切分数据集 # x_t

import numpy as np train_data = np.genfromtxt('Churn-Modelling.csv',delimiter=',',dtype=np.str) test_data = np.genfromtxt('Churn-Modelling-Test-Data.csv',delimiter=',',dtype=np.str) x_train = train_data[1:,:-1] y_train = train_data[1:,-1].astype(int) ...

from sklearn.datasets import load_boston import numpy as np import pandas as pd import matplotlib.pyplot as plt from sklearn.linear_model import LassoCV import seaborn as sns house = load_boston() print(house.DESCR) x = house.data y = house.target d

支持向量机SVM(Support Vector Machines) SVM简单例子 from sklearn import svm x = [[3, 3], [4, 3], [1, 1]] y = [1, 1, -1] model = svm.SVC(kernel='linear') model.fit(x, y) # 打印支持向量 print(model.support_vectors_) # 第2和第0个点是支持向量 print(model.support_)

主成分分析PCA(Principal Component Analysis) PCA-简单例子 import numpy as np import matplotlib.pyplot as plt # 载入数据 data = np.genfromtxt("data.csv", delimiter=",") x_data = data[:,0] y_data = data[:,1] plt.scatter(x_data,y_data) plt.show() print(x_data

聚类算法 K-MEANS python实现K-MEANS import numpy as np import matplotlib.pyplot as plt # 载入数据 data = np.genfromtxt("kmeans.txt", delimiter=" ") plt.scatter(data[:,0],data[:,1]) plt.show() 训练模型 # 计算距离 def euclDistance(vector1, vector2): re

贝叶斯分析 贝叶斯-iris # 导入算法包以及数据集 import numpy as np from sklearn import datasets from sklearn.model_selection import train_test_split from sklearn.metrics import classification_report,confusion_matrix from sklearn.naive_bayes import Multinomi

集成学习Ensemble Learning bagging # 导入算法包以及数据集 from sklearn import neighbors from sklearn import datasets from sklearn.ensemble import BaggingClassifier from sklearn import tree from sklearn.model_selection import train_test_split import numpy as np impo

决策树Decision Tree 决策树-例子 from sklearn.feature_extraction import DictVectorizer from sklearn import tree from sklearn import preprocessing import csv # 读入数据 Dtree = open(r'AllElectronics.csv', 'r') reader = csv.reader(Dtree) # 获取第一行数据 headers =

KNN算法实现 import matplotlib.pyplot as plt import numpy as np import operator # 已知分类的数据 x1 = np.array([3,2,1]) y1 = np.array([104,100,81]) x2 = np.array([101,99,98]) y2 = np.array([10,5,2]) scatter1 = plt.scatter(x1,y1,c='r') scatter2 = plt.scatter(x2...

神经网络

逻辑回归 正确率/召回率/F1指标 梯度下降法-逻辑回归 import matplotlib.pyplot as plt import numpy as np from sklearn.metrics import classification_report from sklearn import preprocessing # 数据是否需要标准化 scale = True # 载入数据 data = np.genfromtxt("LR-testSet.csv",

import numpy as np from numpy import genfromtxt from sklearn import linear_model # 读入数据 data = genfromtxt(r"longley.csv",delimiter=',') print(data) # 切分数据 x_data = data[1:,2:] y_data = data[1:,1] print(x_data) print(y_data) # 创建模型 model = linear_mo..

import numpy as np from numpy import genfromtxt from sklearn import linear_model # 读入数据 data = genfromtxt(r"longley.csv",delimiter=',') print(data) # 切分数据 x_data = data[1:,2:] y_data = data[1:,1] print(x_data) print(y_data) # 创建模型 model = linear_...

岭回归Ridge Regression 标准方程法-岭回归 import numpy as np from numpy import genfromtxt import matplotlib.pyplot as plt # 读入数据 data = genfromtxt(r"longley.csv",delimiter=',') print(data) # 切分数据 x_data = data[1:,2:] y_data = data[1:,1,np.newaxis] print(x_da

特征缩放交叉验证法 过拟合(Overfitting)正则化(Regularized)

标准方程法Normal Equation import numpy as np from numpy import genfromtxt import matplotlib.pyplot as plt # 载入数据 data = np.genfromtxt("data.csv", delimiter=",") x_data = data[:,0,np.newaxis] y_data = data[:,1,np.newaxis] plt.scatter(x_data,y_data) pl

多项式回归 import numpy as np import matplotlib.pyplot as plt from sklearn.preprocessing import PolynomialFeatures from sklearn.linear_model import LinearRegression # 载入数据 data = np.genfromtxt("job.csv", delimiter=",") x_data = data[1:,1] y_data = data[1:,2

矩阵运算 多元线性回归 梯度下降法-多元线性回归 import numpy as np from numpy import genfromtxt import matplotlib.pyplot as plt from mpl_toolkits.mplot3d import Axes3D # 读入数据 data = genfromtxt(r"Delivery.csv",delimiter=',') print(data) # 切分数据 x_data = data[:

回归分析 Regression 一元线性回归 • 回归分析(regression analysis)用来建立方程模拟两 个或者多个变量之间如何关联 • 被预测的变量叫做：因变量(dependent variable), 输出(output) • 被用来进行预测的变量叫做： 自变量(independent variable), 输入(input) • 一元线性回归包含一个自变量和一个因变量 • 以上两个变量的关系用一条直线来模拟 • 如果包含两个以上的自变量，则称作多元回归分析 (multiple re