#导入程序包
import pandas as pd
import pandas_profiling
#导入数据
# df = pd.read_excel("data.xlsx")
df = pd.read_csv("data.csv", header = 0)
df
#启动pandas_profiling
profile = pandas_profiling.ProfileReport(df)
profile
#导出为网页
with open("report.html", "w") as f:
    f.write(profile.to_html())

import matplotlib.pyplot as plt 
y2 = [2,6,11,20,40]
L1, =plt.plot(x,y,color='blue',\
  linewidth=2,linestyle='--',\
  marker='*',markersize=10)
L2, =plt.plot(x,y2,color='blue',\
  linewidth=2,linestyle='-',\
  marker='s',markersize=10)
plt.title('My test')
plt.xlabel('Value')
plt.ylabel('result')
plt.xlim([1,5])
plt.ylim([1,40])
plt.legend([L1,L2,],['Line1','Line2'])
#xy(3,11)指箭头指向的位置，xytext是箭头起始的标注位置
plt.annotate('local max',xy=(3,11),xytext=(3.5,26),\
    xycoords='data',arrowprops=dict(facecolor='c',width=1))
plt.show()

import matplotlib.pyplot as plt
labels = 'frogs','hogs','dogs','logs'
size = 15,30,45,10
colors = 'yellowgreen','gold','lightskyblue','lightcoral'
explode = 0,0.1,0,0
plt.pie(size,explode=explode,labels=labels,colors=colors,shadow=True)
plt.show()

import matplotlib.pyplot as plt
x = [1,2,3,4,5]
y = [1,4,9,16,25]
plt.bar(x,y,facecolor='g')
for x,y in zip(x,y):
    plt.text(x,y,'{f}'.format(f=y),ha='center',va='bottom')
plt.show()

import numpy as np
value = np.random.randint(1,100,10)
print(value)

import numpy as np
import matplotlib.pyplot as plt
value = np.random.randint(1,100,10)
x = np.random.randint(1,100,10)
y = np.random.randint(1,100,10)
plt.scatter(x,y,s=200,c=value,alpha=0.7)
i,j =0,0
while i <=8:
    j = 0
    while j<=8:
        d = (x[i]-x[j+1])**2 + (y[i]-y[j+1])**2
        if d <= 2500:
            plt.plot([x[1],x[j+1]],[y[i],y[j+1]])
        j = j+1
    i = i+1
plt.show()

import pandas as pd
df = pd.read_csv('H:/x.csv',usecols=['subdate','temperature','humidity'])
#查看数据
print(df)
print(df.dtypes)
print(df.colums)
print(df.index)
print(df.values)
#1指pandas的自动标序缩影的序号，先列后行
print(df['tempetature'][1])
#先行后列，-1表示最后一行
print(df,iloc[1:5,1])
#转为日期类型
df['subdate'] = pd.to_datetime(df['subdate'])
#绘图
df.plot(x='subdate',y='temperature',rot='45')
plot.show()
#处理缺失，日期缺失
#生成连续日期
dateindex = pd.date_range(start='20140101',end='20140110')
#将系统的缩影改为日期
df.index = df['subdate']
#重新设置缩影
#重设缩影后就可以发现缺失的日期了
df = df.reindex(dateindex)
#以0行为索引寻找缺失值
print(np.where(pd.isna(df))[0])
#寻找缺失行的行标
print(df.index(np.where(pd.isna(df))[0])
#用0填充缺失值
df = df.fillna(0)
#使用后面的一个值填充，'pad'为前一个值
df = df.fillna(method='bfill')
#填充平均值
for i in np.where(pd.isna(df))[0]:
	df.iloc[i,1] = (df.iloc[i-1,1] + df.iloc[i+1,1])/2
print(df)
#筛选异常数据
error_temperature = df['temperature']
error_temperature_list = error_temperature[(12 < error_temperature) | (error_temperature < 6)]
print(error_temperature_list)
print(error_temperature_list.index)
#数据缺失与异常的位置全部设置为’NaN‘
#对’NaN‘处进行数据填充
for i in error_temperature_list.index:
	df['temperature'][i] = 'NaN'
print(df)
#删除列
df = df.drop(['subdate'],axis = 1)

import pandas as pd
import numpy as np
import matplotlib.pylab as plt
x = np.arange(1,10,1)
y = x*0.9+np.sin(x)
plt.plot(x,y,'o')
plt.show()
#deg=1是一阶，一次回归
model = np.polyfit(x,y,deg=1)
print(model)
#0.5为步长
x2 = np.arange(-2,12,0.5)
y2 = np.polyval(model,x2)
plt.plot(x,y,'o',x2,y2,'*')
plt.show()

df = pd.read_csv('H:/python/yiqing.csv',usecols=['编号‘,'累计‘],encoding='GBK')
plt.plot(df.iloc[:,1],df.iloc[:,0],'o')
plt.show()
x = df.iloc[:75,1]
y = df.iloc[:75,0]
model = np.polyfit(x,y,deg=2)
x2 = np.range(1,100,1)
y2 = np.polyval(model,x2)
print(y2)
plt.plot(x,y,'o',x2,y2,'*')

df = pd.read_csv('H:/python/fenlei.csv')
print(df,head())
train_x=df.iloc[0:80,2:4]
train_y=df.iloc[0:80,1]
from sklearn import neighbors
model = neighbors.KNeighborsClassifier()
model.fit(train_x,train_y)
#看k值
print(model.fit(train_x,train_y))
#预测
test_x = df.iloc[80:100,2:4]
test_p = model.predict(test_x)
print(test_p)
#对比一下
test_y = df.iloc[80:100,1].values
print(test_y)
#打分
p = model.score(test_x,test_y)
print(p)

df = pd.read_csv('H:/python/fenlei.csv')
train_x = df.iloc[0:80,2:4]
train_x2 = np.array(train_x[['yuwen','shuxue']])
#看看形式
print(train_x2.shape)
from sklearn.cluster import KMeans
model = KMeans(n_clusters=3)
print(model)
print(model.labels_)
train_y = df.iloc[0:80,1]
#聚类形成的中心
print(model.cluster_centers_)
plt.plot(df.iloc[0:80,2],df.iloc[0:80,3],'o')
plt.show()
#绘制好看的彩图
def showCluster(dataSet, k, centroids, clusterAssment):
    numSamples, dim = dataSet.shape
    if dim != 2:
        print("Sorry! I can not draw because the dimension of your data is not 2!")
        return 1
    mark = ['or','ob','og','ok','^r','+r','sr','dr','<r','pr']
    if k > len(mark):
        print("Sorry! Your k is too large!")
        return 1
    for i in range(numSamples):
        markIndex = int(clusterAssment[i,0])
        plt.plot(dataSet[i,0],dataSet[i,1],mark[markIndex])
    mark = ['Dr','Db','Dg','Dk','^b','+b','sb','db','<b','pb']
    for i in range(k):
        plt.plot(centroids[i,0],centroids[i,1],mark[i],markeredgecolor='k',markersize=15)
    plt.show()
train_x_array = np.array(train_x[['yuwen','shuxue']])
showCluster(train_x_array,3,model.cluster_centers_,model.lebels_.reshape(-1,1))

df = pd.read_csv('H:/python/fenlei.csv')
train_x = df.iloc[0:80,2:4]
train_y=df.iloc[0:80,1]
from sklearn import tree
#用信息熵
model = tree.DecisionTreeClassifier(criterion='entropy')
model.fit(train_x,train_y)
test_x = df.iloc[80:100,2:4]
test_p = model.predict(test_x)
print(test_p)