def test(inx, path):
'''
:param inx: 待测向量
:param path: 数据路径
:return: 结果
'''
da = ParseData(path)
dataset = da.dataset()
labels = da.labels()
p0vect, p1vect, negative_prop, positive_prob = actual_trainnb0(
dataset, labels)
result = classifyNB(inx, p0vect, p1vect, negative_prop, positive_prob)
return result
from classification.decision_tree.tree import createtree from parsedata.parsedata import ParseData file_path = r'F:\machine\file\Book1.xlsx' labels = ['a', 'b', 'c', 'd'] da = ParseData(file_path) data = da.entry_data() # dataset是整个数据，labels是特征，因为numpy不会显示特征名字，所以另外输入 result = createtree(data, labels) print(result)
from simplify_data.simple_svd.svd import recommend
from parsedata.parsedata import ParseData
import numpy
file_path = r'F:\machine\file\hyxd_movie_01newdata4.xlsx'
data = ParseData(file_path)
da = numpy.mat(data.dataset())
print(recommend(
da,
1,
))
import numpy
import pandas
from classification.adaboost.adboost_tree import adaclassify
from classification.adaboost.adboost_tree import addbosttrainds
from parsedata.parsedata import ParseData
inx = numpy.array([])
file_path = r'F:\machine\file\hyxd_movie_01newdata4.xlsx'
da = ParseData(file_path)
data = da.dataset()
# classlabels=da.labels()
classlabels = numpy.mat(
pandas.read_excel(file_path).iloc[:, [-1]]) #过一会改parsedata，两个返回的维度不一样
classifierarr = addbosttrainds(data, classlabels)
print(classifierarr)
print(adaclassify(inx, classifierarr))
from unsupervised.kmean.kme import kmeans from unsupervised.kmean.dichotomy_tree import dichmeans from parsedata.parsedata import ParseData import numpy file_path=r'F:\machine\file\hyxd_movie_01newdata4.xlsx' test_path=r'F:\machine\file\hyxd_movie_01newdata3.xlsx' da = ParseData(test_path) data=da.entry_data()[:107,:] print(kmeans(data,2)) print(dichmeans(numpy.array(data),5))#这样就对了，好奇怪，明天专门研究一下这些格式问题和相互赋值问题 # data=[[1,2,3],[23,35,56,],[34,1],[23,45,78,],[12,289,],[12,56,17],[34,67,89,],[3,34,12],[16,47,89,],[45,78,89]] # print(dichmeans(numpy.mat(data),5))#这样是对的，奇怪
from tree_logistic.cart_tree import creattree from parsedata.parsedata import ParseData from predict_value.tree_logistic.prune import prune file_path = r'F:\machine\file\hyxd_movie_01newdata4.xlsx' test_path = r'F:\machine\file\hyxd_movie_01newdata5.xlsx' da = ParseData(file_path) data = da.entry_data() test = ParseData(test_path) testdata = test.entry_data() tree = creattree(data) print(tree) print(prune(tree, testdata))
import numpy as np from classification.k_neighborhood.knn import classify from parsedata.parsedata import ParseData file_path=r'F:\machine\file\Book1.xlsx' file_path1=r'F:\machine\file\yob1893.txt' da=ParseData(file_path) dataset=da.dataset() labels=da.labels() inx=np.array([1,2,3,5]) classify(inx,dataset,labels,3)
from parsedata.parsedata import autonorm from parsedata.parsedata import ParseData from predict_value.logistics_value.stand_logis import standRegres file_path = r'F:\machine\file\hyxd_movie_01newdata4.xlsx' da = ParseData(file_path) datamatin = da.dataset() datamatin = autonorm(datamatin) classlabels = da.labels() print(standRegres(datamatin, classlabels))