├── L1 ├── homework │ ├── action1.py │ ├── action2.py │ └── action3.py ├── t1.py ├── t10.py ├── t2.py ├── t3.py ├── t4.py ├── t5.py ├── t6.py ├── t7.py ├── t8.py ├── t9.py └── topn.py ├── L2 ├── dataframe │ ├── dataframe1.py │ ├── dataframe2.py │ ├── dataframe3.py │ ├── dataframe4.py │ ├── dataframe5.py │ ├── heros.csv │ ├── heros.xlsx │ ├── heros2.csv │ ├── result.csv │ └── result.xlsx ├── file_read │ ├── file_read1.py │ ├── file_read2.py │ ├── imagenet_class.csv │ └── temp.txt ├── homework │ └── Action.md ├── map │ ├── map1.py │ └── map2.py ├── regression │ ├── 000001.csv │ ├── 300005.csv │ ├── diabetes_regression.py │ ├── random_regression.py │ └── stock_regression.py ├── series │ └── series1.py ├── show │ ├── bar_show.py │ ├── shanghai_index_1990_12_19_to_2020_03_12.csv │ └── stock_show.py ├── syntax_tree │ ├── expr_syntax.py │ └── hero_syntax.py └── time │ └── time1.py ├── L3 ├── MarketBasket │ └── Market_Basket_Optimisation.csv ├── PythonEDA │ ├── dash1.py │ ├── flask1.py │ ├── python_eda.py │ ├── subplot1.py │ ├── test.csv │ ├── titanic_eda.py │ └── train.csv ├── echarts │ ├── bar1.html │ ├── bar1.py │ ├── line.py │ ├── page.py │ ├── pie.py │ ├── radar.py │ ├── render.html │ ├── rose.py │ └── temp.html ├── feiyan_data │ ├── country_data.csv │ ├── download_dxy_foreign_data_csv.py │ ├── download_qq_foreign_data_csv.py │ └── foreign_country_data.csv ├── feiyan_flask │ ├── App │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-36.pyc │ │ │ ├── __init__.cpython-37.pyc │ │ │ ├── __init__.cpython-38.pyc │ │ │ ├── ext.cpython-36.pyc │ │ │ ├── ext.cpython-37.pyc │ │ │ ├── ext.cpython-38.pyc │ │ │ ├── models.cpython-36.pyc │ │ │ └── models.cpython-37.pyc │ │ ├── ext.py │ │ ├── models.py │ │ ├── static │ │ │ ├── common │ │ │ │ ├── china.js │ │ │ │ ├── echarts.js │ │ │ │ ├── echarts.min.js │ │ │ │ └── jq.js │ │ │ ├── js │ │ │ │ ├── axis.js │ │ │ │ └── map.js │ │ │ └── json │ │ │ │ ├── china.json │ │ │ │ ├── italy.json │ │ │ │ ├── japan.json │ │ │ │ ├── korea.json │ │ │ │ ├── name.json │ │ │ │ └── world.json │ │ ├── templates │ │ │ └── feiyan.html │ │ └── views │ │ │ ├── __init__.py │ │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-36.pyc │ │ │ ├── __init__.cpython-37.pyc │ │ │ ├── __init__.cpython-38.pyc │ │ │ ├── api.cpython-36.pyc │ │ │ └── api.cpython-37.pyc │ │ │ ├── api.py │ │ │ ├── country_data.csv │ │ │ └── foreign_country_data.csv │ ├── __pycache__ │ │ ├── manage.cpython-36.pyc │ │ ├── manage.cpython-37.pyc │ │ └── manage.cpython-38.pyc │ ├── manage.py │ ├── nohup.out │ ├── uwsgi.ini │ ├── uwsgi.log │ └── uwsgi.pid ├── find_median.py ├── homework │ ├── Action1.md │ ├── Market_Basket_Optimisation.csv │ ├── word_cloud1.py │ └── wordcloud.jpg └── wordcloud │ ├── movies.csv │ └── movies_word_cloud.py └── L4 ├── anjuke ├── anjuke_bs.py ├── anjuke_selenium.py ├── auto_login.py └── bs_demo.py ├── pagerank ├── Aliases.csv ├── Emails.csv ├── Persons.csv ├── email_pagerank.py ├── networkx_pagerank.py └── pagerank_simulation.py ├── scc └── scc1.py ├── team_cluster ├── team_cluster.py └── team_cluster_data.csv ├── textrank ├── news.txt ├── news_textrank.py ├── news_textrank_snownlp.py └── sentence_textrank.py └── valid_tree ├── valid_tree.py └── valid_tree2.py /L1/homework/action1.py: -------------------------------------------------------------------------------- 1 | # A+B Problem 2 | while True: 3 | try: 4 | line = input() 5 | a = line.split() 6 | print(int(a[0])+int(a[1])) 7 | except: 8 | break -------------------------------------------------------------------------------- /L1/homework/action2.py: -------------------------------------------------------------------------------- 1 | # 求2+4+6+8+...+100的求和 2 | sum = 0 3 | for i in range(2, 100+1, 2): 4 | sum = sum + i 5 | print(sum) 6 | -------------------------------------------------------------------------------- /L1/homework/action3.py: -------------------------------------------------------------------------------- 1 | # Action3: 统计全班的成绩 2 | import numpy as np 3 | 4 | scoretype = np.dtype({'names': ['name', 'chinese', 'math', 'english'], 5 | 'formats': ['U32', 'i', 'i', 'i']}) 6 | peoples = np.array( 7 | [ 8 | ("张飞", 68, 65, 30), 9 | ("关羽", 95, 76, 98), 10 | ("刘备", 98, 86, 88), 11 | ("典韦", 90, 88, 77), 12 | ("许褚", 80, 90, 90) 13 | ], dtype=scoretype) 14 | print("科目 | 平均成绩 | 最小成绩 | 最大成绩 | 方差 | 标准差") 15 | courses = {'语文': peoples[:]['chinese'], 16 | '英文': peoples[:]['english'], '数学': peoples[:]['math']} 17 | for course, scores in courses.items(): 18 | print(course, np.mean(scores), np.amin(scores), np.amax(scores), np.std(scores), 19 | np.var(scores)) 20 | print('Ranking:') 21 | ranking = sorted(peoples, key=lambda x: x[1]+x[2]+x[3], reverse=True) 22 | print(ranking) -------------------------------------------------------------------------------- /L1/t1.py: -------------------------------------------------------------------------------- 1 | # 输入与输出 2 | name = input("What's your name?") 3 | sum = 100+100 4 | print ('hello,%s' %name) 5 | print ('sum = %d' %sum) 6 | -------------------------------------------------------------------------------- /L1/t10.py: -------------------------------------------------------------------------------- 1 | # numpy中统计函数的使用 2 | import numpy as np 3 | # 最大、最小值 4 | def work1(): 5 | a = np.array([[1,2,3], [4,5,6], [7,8,9]]) 6 | print(np.min(a)) 7 | print(np.min(a,0)) 8 | print(np.min(a,1)) 9 | print(np.max(a)) 10 | print(np.max(a,0)) 11 | print(np.max(a,1)) 12 | 13 | # 统计百分位数 14 | def work2(): 15 | a = np.array([[1,2,3], [4,5,6], [7,8,9]]) 16 | print(np.percentile(a, 50)) 17 | print(np.percentile(a, 50, axis=0)) 18 | print(np.percentile(a, 50, axis=1)) 19 | 20 | # 中位数、平均数 21 | def work3(): 22 | a = np.array([[1,2,3], [4,5,6], [7,8,9]]) 23 | #求中位数 24 | print(np.median(a)) 25 | print(np.median(a, axis=0)) 26 | print(np.median(a, axis=1)) 27 | #求平均数 28 | print(np.mean(a)) 29 | print(np.mean(a, axis=0)) 30 | print(np.mean(a, axis=1)) 31 | 32 | # 加权平均值 33 | def work4(): 34 | a = np.array([1,2,3,4]) 35 | weights = np.array([1,2,3,4]) 36 | print(np.average(a)) 37 | print(np.average(a,weights=weights)) 38 | 39 | # 标准差、方差 40 | def work5(): 41 | a = np.array([1,2,3,4]) 42 | print(np.std(a)) 43 | print(np.var(a)) 44 | 45 | # 对数组进行排序 46 | def work6(): 47 | a = np.array([[4,3,2],[2,4,1]]) 48 | print(np.sort(a)) 49 | print(np.sort(a, axis=None)) 50 | print(np.sort(a, axis=0)) 51 | print(np.sort(a, axis=1)) 52 | print(type(a)) 53 | 54 | # 对数组进行排序 55 | def work7() 56 | # 使用List进行排序 57 | a = [4,3,2,2,4,1] 58 | print(type(a)) 59 | a.sort() 60 | print(a) 61 | a.sort(reverse=True) 62 | print(a) 63 | 64 | #work1() 65 | #work2() 66 | #work3() 67 | #work4() 68 | #work5() 69 | work6() 70 | -------------------------------------------------------------------------------- /L1/t2.py: -------------------------------------------------------------------------------- 1 | # 条件判断 2 | score = 95 3 | if score>= 90: 4 | print('Excellent') 5 | else: 6 | if xscore < 60: 7 | print('Fail') 8 | else: 9 | print('Good Job') -------------------------------------------------------------------------------- /L1/t3.py: -------------------------------------------------------------------------------- 1 | # for循环 2 | sum = 0 3 | for number in range(11): 4 | sum = sum + number 5 | print(sum) 6 | 7 | 8 | # while循环 9 | sum = 0 10 | number = 1 11 | while number < 11: 12 | sum = sum + number 13 | number = number + 1 14 | print(sum) -------------------------------------------------------------------------------- /L1/t4.py: -------------------------------------------------------------------------------- 1 | # 列表 2 | lists = ['zhangfei','guanyu','liubei'] 3 | # 列表中添加元素 4 | lists.append('dianwei') 5 | print(lists) 6 | print(len(lists)) 7 | # 在指定位置添加元素 8 | lists.insert(0,'diaochan') 9 | # 删除末尾元素 10 | lists.pop() 11 | print(lists) -------------------------------------------------------------------------------- /L1/t5.py: -------------------------------------------------------------------------------- 1 | # 元组的使用 2 | tuples = ('zhangfei','65') 3 | print(tuples[0]) 4 | 5 | # 返回字典key组成的元组 6 | print(tuple({'zhangfei':65, 'guanyu':99})) 7 | 8 | # 列表转化为元组 9 | temp_list = [123, 'zhangfei', 'guanyu', 'liubei']; 10 | temp_tuple = tuple(temp_list) 11 | print(temp_tuple) 12 | -------------------------------------------------------------------------------- /L1/t6.py: -------------------------------------------------------------------------------- 1 | # 字典的使用 2 | #定义一个dictionary 3 | score = {'guanyu':96,'zhangfei':95} 4 | 5 | #添加一个元素 6 | score['zhaoyun'] = 98 7 | print(score) 8 | 9 | #删除一个元素 10 | score.pop('zhangfei') 11 | 12 | #查看key是否存在 13 | print('zhangfei' in score) 14 | 15 | #查看一个key对应的值 16 | print(score.get('zhangfei')) 17 | print(score.get('dianwei',99)) -------------------------------------------------------------------------------- /L1/t7.py: -------------------------------------------------------------------------------- 1 | # 集合的使用 2 | s = set(['zhangfei', 'guanyu', 'liubei']) 3 | s.add('diaowei') 4 | s.remove('zhangfei') 5 | print(s) 6 | print('liubei' in s) -------------------------------------------------------------------------------- /L1/t8.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | # ndarray使用 3 | def work1(): 4 | a = np.array([1, 2, 3]) 5 | b = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]]) 6 | b[1,1]=10 7 | print(a.shape) 8 | print(b.shape) 9 | print(a.dtype) 10 | print(b) 11 | 12 | # 结构化数组的使用 13 | def work2(): 14 | persontype = np.dtype({'names':['name', 'age', 'chinese', 'math', 'english'], \ 15 | 'formats':['S32','i', 'i', 'i', 'f']}) 16 | peoples = np.array([("ZhangFei",32,75,100, 90),("GuanYu",24,85,96,88.5), \ 17 | ("ZhaoYun",28,85,92,96.5),("HuangZhong",29,65,85,100)], dtype=persontype) 18 | ages = peoples['age'] 19 | chineses = peoples['chinese'] 20 | maths = peoples['math'] 21 | englishs = peoples['english'] 22 | print(np.mean(ages)) 23 | print(np.mean(chineses)) 24 | print(np.mean(maths)) 25 | print(np.mean(englishs)) 26 | 27 | #work1() 28 | work2() 29 | 30 | 31 | -------------------------------------------------------------------------------- /L1/t9.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | 3 | # 连续数组的创建：arange 或 linspace 4 | x1 = np.arange(1,11,2) 5 | x2 = np.linspace(1,9,5) 6 | print('x1=', x1) 7 | print('x2=', x2) 8 | 9 | print(np.add(x1, x2)) 10 | print(np.subtract(x1, x2)) 11 | print(np.multiply(x1, x2)) 12 | print(np.divide(x1, x2)) 13 | print(np.power(x1, x2)) 14 | print(np.remainder(x1, x2)) -------------------------------------------------------------------------------- /L1/topn.py: -------------------------------------------------------------------------------- 1 | """ 2 | 算法面试：10亿个数中取TOP-1000个数 3 | 堆的性质：每一个节点比它的左右子节点小， 4 | 先取前N个数，构成小顶堆，即在内存中维护一个1000数的小顶堆 5 | 然后对文件中读取数据，和堆顶比较： 6 | if 比堆顶小，则丢弃 7 | if 比堆顶大，替换根节点，并且调整堆，保持小顶堆的性质 8 | 所有数据处理完，得到的即是Top-N 9 | """ 10 | 11 | class TopN: 12 | # 父节点下标 13 | def parent(self, n): 14 | return int((n - 1) / 2) 15 | 16 | # 左节点下标 17 | def left(self, n): 18 | return 2 * n + 1 19 | 20 | # 右节点下标 21 | def right(self, n): 22 | return 2 * n + 2 23 | 24 | # 构建小顶堆，保证父节点小于左右子节点 25 | def buildHeap(self, n, data): 26 | for i in range(1, n): 27 | t = i 28 | # 调整堆，如果节点比父亲节点小，则交换 29 | while t != 0 and data[t] < data[self.parent(t)]: 30 | temp = data[t] 31 | data[t] = data[self.parent(t)] 32 | data[self.parent(t)] = temp 33 | t = self.parent(t) 34 | print(data) 35 | 36 | # 调整data[i] 37 | def adjust(self, i, n, data): 38 | # 小于堆的根节点，不调整 39 | if data[i] <= data[0]: 40 | return 41 | 42 | # 置换堆顶 43 | temp = data[i] 44 | data[i] = data[0] 45 | data[0] = temp 46 | # 调整堆顶 47 | t = 0 48 | while (self.left(t) < n and data[self.left(t)] < data[t]) or (self.right(t) < n and data[self.right(t)] < data[t]): 49 | if self.right(t) < n and data[self.right(t)] < data[self.left(t)]: 50 | # 右孩子更小，置换右孩子 51 | temp = data[t] 52 | data[t] = data[self.right(t)] 53 | data[self.right(t)] = temp 54 | t = self.right(t) 55 | else: 56 | # 否则置换左孩子 57 | temp = data[t] 58 | data[t] = data[self.left(t)] 59 | data[self.left(t)] = temp 60 | t = self.left(t) 61 | 62 | # 寻找topN，调整data，将topN排到最前面 63 | def findTopN(self, n, data): 64 | # 先构建n个数的小顶堆 65 | self.buildHeap(n, data); 66 | # n往后的数进行调整 67 | for i in range(n, len(data)): 68 | self.adjust(i, n, data) 69 | return data 70 | 71 | 72 | # 第一组测试 12个 73 | arr1 = [58, 26, 45, 18, 22, 39, 96, 75, 80, 65, 63, 28] 74 | print("原数组：" + str(arr1)) 75 | topn = TopN() 76 | result = topn.findTopN(5, arr1) 77 | print("数组进行Top-N调整：" + str(result)) 78 | 79 | # 第二组测试 随机100个 80 | """ 81 | import random 82 | tempList = [] 83 | for i in range(100): 84 | temp = random.randint(0, 1000) 85 | tempList.append(temp) 86 | print("原数组：" + str(tempList)) 87 | topn = TopN() 88 | result = topn.findTopN(5, tempList) 89 | print("数组进行Top-N调整：" + str(result)) 90 | 91 | """ -------------------------------------------------------------------------------- /L2/dataframe/dataframe1.py: -------------------------------------------------------------------------------- 1 | # dataframe使用 2 | from pandas import Series, DataFrame 3 | data = {'Chinese': [66, 95, 93, 90,80], 'Math': [30, 98, 96, 77, 90], 'English': [65, 85, 92, 88, 90]} 4 | df1 = DataFrame(data) 5 | df2 = DataFrame(data, index=['ZhangFei', 'GuanYu', 'LiuBei', 'DianWei', 'XuChu'], columns=['Chinese', 'Math', 'English']) 6 | print(df1) 7 | print(df2) 8 | 9 | # 对列名进行更换 10 | df2.rename(columns={'Chinese': '语文', 'English': '英语', 'Math': '数学'}, inplace = True) 11 | print(df2.isnull()) 12 | # 输出df2的概要 13 | print(df2.describe()) 14 | 15 | -------------------------------------------------------------------------------- /L2/dataframe/dataframe2.py: -------------------------------------------------------------------------------- 1 | import pandas as pd 2 | from pandas import Series, DataFrame 3 | 4 | # 读取xlsx文件 5 | score = DataFrame(pd.read_excel('heros.xlsx')) 6 | score.to_excel('result.xlsx') 7 | print(score) 8 | # 读取csv文件 9 | score = pd.read_csv('heros.csv') 10 | score.to_csv('result.csv') 11 | -------------------------------------------------------------------------------- /L2/dataframe/dataframe3.py: -------------------------------------------------------------------------------- 1 | import pandas as pd 2 | from pandas import DataFrame 3 | 4 | df1 = DataFrame({'name':['ZhangFei', 'GuanYu', 'a', 'b', 'c'], 'data1':range(1,6)}) 5 | df2 = DataFrame({'name':['ZhangFei', 'GuanYu', 'A', 'B', 'C'], 'data2':range(1,6)}) 6 | #print(df1) 7 | #print(df2) 8 | df3 = pd.merge(df1, df2, on='name') 9 | #print(df3) 10 | df3 = pd.merge(df1, df2, how='inner') 11 | #print(df3) 12 | df3 = pd.merge(df1, df2, how='left') 13 | df3 = pd.merge(df1, df2, how='right') 14 | #print(df3) 15 | df3 = pd.merge(df1, df2, how='outer') 16 | print(df3) 17 | -------------------------------------------------------------------------------- /L2/dataframe/dataframe4.py: -------------------------------------------------------------------------------- 1 | # DataFrame练习 2 | from pandas import Series, DataFrame 3 | data = {'Chinese': [66, 95, 93, 90,80], 'Math': [30, 98, 96, 77, 90], 'English': [65, 85, 92, 88, 90]} 4 | df = DataFrame(data, index=['ZhangFei', 'GuanYu', 'LiuBei', 'DianWei', 'XuChu'], columns=['Chinese', 'Math', 'English']) 5 | 6 | # 提取Index为ZhangFei的行 7 | print(df.loc['ZhangFei']) 8 | # 提取第0行 9 | print(df.iloc[0]) 10 | 11 | # 提取列为English的所有行 12 | print(df.loc[:,['English']]) 13 | # 提取第2列的所有行 14 | print(df.iloc[:,2]) 15 | 16 | # 查看ZhangFei, GuanYu的Chinese Math成绩 17 | print(df.loc[['ZhangFei','GuanYu'], ['Chinese','Math']]) 18 | print(df.iloc[[0,1],[0,1]]) -------------------------------------------------------------------------------- /L2/dataframe/dataframe5.py: -------------------------------------------------------------------------------- 1 | # 读取heros2.csv数据表，按照role进行groupby 2 | import numpy as np 3 | import pandas as pd 4 | # 因为文件中有中文，所以采用gbk编码读取 5 | data = pd.read_csv('heros2.csv', encoding='gbk') 6 | 7 | result = data.groupby('role').agg([np.sum, np.mean]) 8 | print(result) 9 | 10 | -------------------------------------------------------------------------------- /L2/dataframe/heros.csv: -------------------------------------------------------------------------------- 1 | ,Chinese,Maths,English 2 | ZhangFei,66,30,65 3 | GuanYu,95,98,85 4 | LiuBei,93,96,92 5 | DianWei,90,77,88 6 | XuChu,80,90,90 7 | -------------------------------------------------------------------------------- /L2/dataframe/heros.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cystanford/Data_Analysis_with_Python/a33b965d98612031a0effe17a9c6da3a1eaefb5e/L2/dataframe/heros.xlsx -------------------------------------------------------------------------------- /L2/dataframe/heros2.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cystanford/Data_Analysis_with_Python/a33b965d98612031a0effe17a9c6da3a1eaefb5e/L2/dataframe/heros2.csv -------------------------------------------------------------------------------- /L2/dataframe/result.csv: -------------------------------------------------------------------------------- 1 | ,Unnamed: 0,Chinese,Maths,English 2 | 0,ZhangFei,66,30,65 3 | 1,GuanYu,95,98,85 4 | 2,LiuBei,93,96,92 5 | 3,DianWei,90,77,88 6 | 4,XuChu,80,90,90 7 | -------------------------------------------------------------------------------- /L2/dataframe/result.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cystanford/Data_Analysis_with_Python/a33b965d98612031a0effe17a9c6da3a1eaefb5e/L2/dataframe/result.xlsx -------------------------------------------------------------------------------- /L2/file_read/file_read1.py: -------------------------------------------------------------------------------- 1 | # 读取imagenet的分类ID说明 2 | 3 | # 读文件 4 | f = open('imagenet_class.csv') 5 | text = f.read() 6 | #print(text) 7 | 8 | # 读文件，按行来读取 9 | f = open('imagenet_class.csv') 10 | lines = f.readlines() 11 | #print(lines) 12 | print(len(lines)) 13 | print(lines[0]) 14 | 15 | # 写文件 16 | f = open('temp.txt', 'w') 17 | f.write('hello world!') 18 | f.close() 19 | -------------------------------------------------------------------------------- /L2/file_read/file_read2.py: -------------------------------------------------------------------------------- 1 | # pandas读取imagenet classID表示 2 | import pandas as pd 3 | classes = pd.read_csv('imagenet_class.csv', sep=',', header=None) 4 | #print(classes) 5 | # 查看id=207的含义 6 | print(classes[classes[0]==207]) 7 | 8 | -------------------------------------------------------------------------------- /L2/file_read/temp.txt: -------------------------------------------------------------------------------- 1 | hello world! -------------------------------------------------------------------------------- /L2/homework/Action.md: -------------------------------------------------------------------------------- 1 | Action1：参考syntax_tree目录中的两个例子 2 | Action2：参考regression目录 3 | -------------------------------------------------------------------------------- /L2/map/map1.py: -------------------------------------------------------------------------------- 1 | # 计算平方数 2 | def square(x): 3 | return x * x 4 | # 计算列表各个元素的平方 5 | print(list(map(square, [1,2,3,4,5]))) 6 | 7 | # lambda函数 8 | add = lambda x, y: x + y 9 | print(add(5, 6)) 10 | 11 | # 按照x[1]进行列表排序 12 | a = [(2, 56), (3, 12), (6, 10), (9, 13)] 13 | a.sort(key=lambda x: x[1]) 14 | print(a) 15 | -------------------------------------------------------------------------------- /L2/map/map2.py: -------------------------------------------------------------------------------- 1 | """ 2 | 新列表 = 原列表的平方 3 | 使用map, lambda两种方法完成 4 | """ 5 | 6 | numbers = [1, 2, 3, 4, 5, 6, 7, 8, 9] 7 | # 计算平方数 8 | def square(x): 9 | return x * x 10 | print(list(map(square, numbers))) 11 | 12 | # 使用lambda定义函数 13 | print(list(map(lambda x: x*x, numbers))) 14 | 15 | -------------------------------------------------------------------------------- /L2/regression/diabetes_regression.py: -------------------------------------------------------------------------------- 1 | """ 2 | 使用sklearn自带的糖尿病数据集，进行回归分析 3 | Diabetes：包含442个患者的10个生理特征（年龄，性别、体重、血压）和一年以后疾病级数指标 4 | """ 5 | from sklearn import datasets 6 | from sklearn import linear_model 7 | from sklearn.model_selection import train_test_split 8 | from sklearn.metrics import mean_squared_error 9 | 10 | # 加载数据 11 | diabetes = datasets.load_diabetes() 12 | data = diabetes.data 13 | # 数据探索 14 | print(data.shape) 15 | print(data[0]) 16 | 17 | # 训练集 70%，测试集30% 18 | train_x, test_x, train_y, test_y = train_test_split(diabetes.data, diabetes.target, test_size=0.3, random_state=14) 19 | print(len(train_x)) 20 | 21 | #回归训练及预测 22 | clf = linear_model.LinearRegression() 23 | clf.fit(train_x, train_y) 24 | 25 | print(clf.coef_) 26 | #print(train_x.shape) 27 | #print(clf.score(test_x, test_y)) 28 | pred_y = clf.predict(test_x) 29 | print(mean_squared_error(test_y, pred_y)) 30 | -------------------------------------------------------------------------------- /L2/regression/random_regression.py: -------------------------------------------------------------------------------- 1 | # 回归分析 2 | import random 3 | from sklearn import linear_model 4 | reg = linear_model.LinearRegression() 5 | 6 | def generate(x): 7 | y = 2*x+10+random.random() 8 | return y 9 | 10 | train_x = [] 11 | train_y = [] 12 | for x in range(1000): 13 | train_x.append([x]) 14 | y = generate(x) 15 | train_y.append([y]) 16 | 17 | reg.fit (train_x, train_y) 18 | # coef_ 保存线性模型的系数w 19 | print(reg.coef_) 20 | print(reg.intercept_) -------------------------------------------------------------------------------- /L2/regression/stock_regression.py: -------------------------------------------------------------------------------- 1 | import statsmodels.api as sm 2 | import statsmodels.formula.api as smf 3 | import statsmodels.graphics.api as smg 4 | import patsy 5 | import matplotlib.pyplot as plt 6 | import numpy as np 7 | import pandas as pd 8 | from pandas import Series,DataFrame 9 | from scipy import stats 10 | import seaborn as sns 11 | import datetime, os, warnings 12 | 13 | warnings.filterwarnings('ignore') 14 | plt.rcParams['font.sans-serif']=['SimHei'] #用来正常显示中文标签 15 | plt.rcParams['axes.unicode_minus'] = False #可以显示负号 16 | 17 | # 设置起始时间 18 | start = datetime.datetime(2019,1,1) 19 | end = datetime.datetime(2019,12,31) 20 | #print(start) 21 | 22 | from pandas_datareader.data import DataReader 23 | # 读取上证综指 及 探路者数据 24 | def load_data(): 25 | if os.path.exists('000001.csv'): 26 | data_ss = pd.read_csv('000001.csv') 27 | data_tlz = pd.read_csv('300005.csv') 28 | else: 29 | # 上证综指 30 | data_ss = DataReader("000001.SS", "yahoo",start,end) 31 | # 300005 探路者股票 深证 32 | data_tlz = DataReader("300005.SZ", "yahoo",start,end) 33 | data_ss.to_csv('000001.csv') 34 | data_tlz.to_csv('300005.csv') 35 | return data_ss, data_tlz 36 | 37 | data_ss, data_tlz = load_data() 38 | 39 | print(data_ss.head()) 40 | print(data_tlz.head()) 41 | 42 | # 探路者与上证综指 43 | close_ss = data_ss["Close"] 44 | close_tlz = data_tlz["Close"] 45 | 46 | # 将探路者与上证综指进行数据合并 47 | stock = pd.merge(data_ss, data_tlz, left_index = True, right_index = True) 48 | stock = stock[["Close_x","Close_y"]] 49 | stock.columns = ["上证综指","探路者"] 50 | 51 | # 统计每日收益率 52 | daily_return = (stock.diff()/stock.shift(periods = 1)).dropna() 53 | print(daily_return.head()) 54 | # 找出当天收益率大于10%的，应该是没有，因为涨停为10% 55 | print(daily_return[daily_return["探路者"] > 0.1]) 56 | 57 | # 每日收益率可视化 58 | fig,ax = plt.subplots(nrows=1,ncols=2,figsize=(15,6)) 59 | daily_return["上证综指"].plot(ax=ax[0]) 60 | ax[0].set_title("上证综指") 61 | daily_return["探路者"].plot(ax=ax[1]) 62 | ax[1].set_title("探路者") 63 | plt.show() 64 | 65 | 66 | # 散点图 67 | fig,ax = plt.subplots(nrows=1,ncols=1,figsize=(12,6)) 68 | plt.scatter(daily_return["探路者"],daily_return["上证综指"]) 69 | plt.title("每日收益率散点图 from 探路者 & 上证综指") 70 | plt.show() 71 | 72 | # 回归分析 73 | import statsmodels.api as sm 74 | # 加入截距项 75 | daily_return["intercept"]=1.0 76 | model = sm.OLS(daily_return["探路者"],daily_return[["上证综指","intercept"]]) 77 | results = model.fit() 78 | print(results.summary()) 79 | 80 | 81 | 82 | -------------------------------------------------------------------------------- /L2/series/series1.py: -------------------------------------------------------------------------------- 1 | # series使用 2 | from pandas import Series, DataFrame 3 | x1 = Series([1,2,3,4]) 4 | x2 = Series(data=[1,2,3,4], index=['a', 'b', 'c', 'd']) 5 | # 使用字典来进行创建 6 | d = {'a':1, 'b':2, 'c':3, 'd':4} 7 | x3 = Series(d) 8 | 9 | print(x1) 10 | print(x2) 11 | print(x3) -------------------------------------------------------------------------------- /L2/show/bar_show.py: -------------------------------------------------------------------------------- 1 | import pandas as pd 2 | import numpy as np 3 | import matplotlib.pyplot as plt 4 | 5 | df = pd.DataFrame(np.random.rand(10,4), columns=['a','b','c','d']) 6 | # 使用bar()生成直方图，barh()生成水平条形图（要生成一个堆积条形图，需要指定stacked=True） 7 | df.plot.bar() 8 | df.plot.bar(stacked=True) 9 | df.plot.barh(stacked=True) 10 | plt.show() -------------------------------------------------------------------------------- /L2/show/stock_show.py: -------------------------------------------------------------------------------- 1 | # 沪市指数回归分析 2 | import numpy as np 3 | import pandas as pd 4 | import matplotlib.pyplot as plt 5 | from statsmodels.tsa.arima_model import ARIMA 6 | import statsmodels.api as sm 7 | import warnings 8 | from itertools import product 9 | from datetime import datetime, timedelta 10 | import calendar 11 | 12 | warnings.filterwarnings('ignore') 13 | plt.rcParams['font.sans-serif']=['SimHei'] #用来正常显示中文标签 14 | # 数据加载 15 | df = pd.read_csv('./shanghai_index_1990_12_19_to_2020_03_12.csv') 16 | df = df[['Timestamp', 'Price']] 17 | 18 | # 将时间作为df的索引 19 | df.Timestamp = pd.to_datetime(df.Timestamp) 20 | df.index = df.Timestamp 21 | # 数据探索 22 | print(df.head()) 23 | # 按照月，季度，年来统计 24 | df_month = df.resample('M').mean() 25 | df_Q = df.resample('Q-DEC').mean() 26 | df_year = df.resample('A-DEC').mean() 27 | print(df_month) 28 | 29 | # 按照天，月，季度，年来显示沪市指数的走势 30 | fig = plt.figure(figsize=[15, 7]) 31 | plt.rcParams['font.sans-serif']=['SimHei'] #用来正常显示中文标签 32 | plt.suptitle('沪市指数', fontsize=20) 33 | plt.subplot(221) 34 | plt.plot(df.Price, '-', label='按天') 35 | plt.legend() 36 | plt.subplot(222) 37 | plt.plot(df_month.Price, '-', label='按月') 38 | plt.legend() 39 | plt.subplot(223) 40 | plt.plot(df_Q.Price, '-', label='按季度') 41 | plt.legend() 42 | plt.subplot(224) 43 | plt.plot(df_year.Price, '-', label='按年') 44 | plt.legend() 45 | plt.show() 46 | -------------------------------------------------------------------------------- /L2/syntax_tree/expr_syntax.py: -------------------------------------------------------------------------------- 1 | # 每个函数，都有env参数 2 | Num = lambda env, n: n 3 | Var = lambda env, x: env[x] 4 | Add = lambda env, a, b:_eval(env, a) + _eval(env, b) 5 | Mul = lambda env, a, b:_eval(env, a) * _eval(env, b) 6 | # 对表达式进行处理，expr[0]为符号，*expr[1:]为传入的参数 7 | _eval = lambda env, expr:expr[0](env, *expr[1:]) 8 | 9 | env = {'a':3, 'b':6} 10 | tree = (Add, (Var, 'a'), 11 | (Mul, (Num, 5), (Var, 'b')) 12 | ) 13 | 14 | print(_eval(env, (Var, 'a'))) 15 | print(_eval(env, (Num, 5))) 16 | print(Num(env, 5)) 17 | print(_eval(env, tree)) 18 | -------------------------------------------------------------------------------- /L2/syntax_tree/hero_syntax.py: -------------------------------------------------------------------------------- 1 | import random 2 | 3 | # 定语从句语法 4 | grammar = ''' 5 | 战斗 => 施法 ， 结果 。 6 | 施法 => 主语 动作 技能 7 | 结果 => 主语 获得 效果 8 | 主语 => 张飞 | 关羽 | 赵云 | 典韦 | 许褚 | 刘备 | 黄忠 | 曹操 | 鲁班七号 | 貂蝉 9 | 动作 => 施放 | 使用 | 召唤 10 | 技能 => 一骑当千 | 单刀赴会 | 青龙偃月 | 刀锋铁骑 | 黑暗潜能 | 画地为牢 | 守护机关 | 狂兽血性 | 龙鸣 | 惊雷之龙 | 破云之龙 | 天翔之龙 11 | 获得 => 损失 | 获得 12 | 效果 => 数值 状态 13 | 数值 => 1 | 1000 |5000 | 100 14 | 状态 => 法力 | 生命 15 | ''' 16 | 17 | # 得到语法字典 18 | def getGrammarDict(gram, linesplit = "\n", gramsplit = "=>"): 19 | #定义字典 20 | result = {} 21 | 22 | for line in gram.split(linesplit): 23 | # 去掉首尾空格后，如果为空则退出 24 | if not line.strip(): 25 | continue 26 | expr, statement = line.split(gramsplit) 27 | result[expr.strip()] = [i.split() for i in statement.split("|")] 28 | #print(result) 29 | return result 30 | 31 | # 生成句子 32 | def generate(gramdict, target, isEng = False): 33 | if target not in gramdict: 34 | return target 35 | find = random.choice(gramdict[target]) 36 | #print(find) 37 | blank = '' 38 | # 如果是英文中间间隔为空格 39 | if isEng: 40 | blank = ' ' 41 | return blank.join(generate(gramdict, t, isEng) for t in find) 42 | 43 | gramdict = getGrammarDict(grammar) 44 | print(generate(gramdict,"战斗")) 45 | print(generate(gramdict,"战斗", True)) 46 | 47 | 48 | -------------------------------------------------------------------------------- /L2/time/time1.py: -------------------------------------------------------------------------------- 1 | # 使用time处理时间 2 | import time 3 | timestamp = time.time() 4 | print("当前时间戳为:", timestamp) 5 | # 转化为struct_time类型 6 | localtime = time.localtime(timestamp) 7 | print("本地时间为 :", localtime) 8 | print(type(localtime)) 9 | 10 | 11 | import datetime 12 | date = datetime.date(2020, 3, 1) 13 | print(date) 14 | 15 | time_now = datetime.datetime.now() 16 | delta1 = datetime.timedelta(days=30) 17 | print(time_now) 18 | print(time_now + delta1) 19 | -------------------------------------------------------------------------------- /L3/PythonEDA/dash1.py: -------------------------------------------------------------------------------- 1 | # 使用dash进行股票可视化交互 2 | import dash 3 | from dash.dependencies import Input, Output 4 | import dash_core_components as dcc 5 | import dash_html_components as html 6 | from datetime import datetime as dt 7 | from pandas_datareader.data import DataReader 8 | import tushare as ts 9 | 10 | # 创建一个应用 11 | app = dash.Dash() 12 | # 设置layout 13 | app.layout = html.Div([ 14 | html.H1('k线图'), 15 | dcc.Dropdown( 16 | id='my-dropdown', 17 | options=[ 18 | {'label': '探路者', 'value':'300005'}, 19 | {'label': '莱美药业', 'value':'300006'}, 20 | {'label': '汉威科技', 'value':'300007'}, 21 | {'label': '天海防务', 'value':'300008'}, 22 | {'label': '安科生物', 'value':'300009'}, 23 | ], 24 | value='300005' 25 | ), 26 | dcc.Graph(id='my-graph') 27 | ]) 28 | 29 | @app.callback(Output('my-graph', 'figure'), [Input('my-dropdown', 'value')]) 30 | def update_graph(selected_dropdown_value): 31 | df = ts.get_k_data(selected_dropdown_value, ktype='30') 32 | return { 33 | 'data':[ 34 | { 35 | 'x': df.index, 36 | 'y':df.close 37 | } 38 | ] 39 | } 40 | 41 | if __name__ == '__main__': 42 | app.run_server(host="0.0.0.0") -------------------------------------------------------------------------------- /L3/PythonEDA/flask1.py: -------------------------------------------------------------------------------- 1 | from flask import Flask 2 | app = Flask(__name__) 3 | 4 | @app.route('/') 5 | def hello_world(): 6 | return '你好，世界！' 7 | 8 | if __name__ == "__main__": 9 | app.run(host='127.0.0.1', port=8080) 10 | -------------------------------------------------------------------------------- /L3/PythonEDA/python_eda.py: -------------------------------------------------------------------------------- 1 | import matplotlib.pyplot as plt 2 | import seaborn as sns 3 | import numpy as np 4 | import pandas as pd 5 | import os 6 | from matplotlib.font_manager import FontProperties 7 | 8 | # 散点图 9 | def scatter(): 10 | # 数据准备 11 | N = 500 12 | x = np.random.randn(N) 13 | y = np.random.randn(N) 14 | # 用Matplotlib画散点图 15 | plt.scatter(x, y,marker='x') 16 | plt.show() 17 | # 用Seaborn画散点图 18 | df = pd.DataFrame({'x': x, 'y': y}) 19 | sns.jointplot(x="x", y="y", data=df, kind='scatter'); 20 | plt.show() 21 | 22 | # 折线图 23 | def line_chart(): 24 | # 数据准备 25 | x = [1900, 1901, 1902, 1903, 1904, 1905, 1906, 1907, 1908, 1909, 1910] 26 | y = [265, 323, 136, 220, 305, 350, 419, 450, 560, 720, 830] 27 | # 使用Matplotlib画折线图 28 | plt.plot(x, y) 29 | plt.show() 30 | # 使用Seaborn画折线图 31 | df = pd.DataFrame({'x': x, 'y': y}) 32 | sns.lineplot(x="x", y="y", data=df) 33 | plt.show() 34 | 35 | # 条形图 36 | def bar_chart(): 37 | # 数据准备 38 | x = ['c1', 'c2', 'c3', 'c4'] 39 | y = [15, 18, 5, 26] 40 | # 用Matplotlib画条形图 41 | plt.bar(x, y) 42 | plt.show() 43 | # 用Seaborn画条形图 44 | sns.barplot(x, y) 45 | plt.show() 46 | 47 | # 箱线图 48 | def box_plots(): 49 | # 数据准备 50 | # 生成0-1之间的20*4维度数据 51 | data=np.random.normal(size=(10,4)) 52 | lables = ['A','B','C','D'] 53 | # 用Matplotlib画箱线图 54 | plt.boxplot(data,labels=lables) 55 | plt.show() 56 | # 用Seaborn画箱线图 57 | df = pd.DataFrame(data, columns=lables) 58 | sns.boxplot(data=df) 59 | plt.show() 60 | 61 | # 饼图 62 | def pie_chart(): 63 | # 数据准备 64 | nums = [25, 33, 37] 65 | # 射手adc：法师apc：坦克tk 66 | labels = ['ADC','APC', 'TK'] 67 | # 用Matplotlib画饼图 68 | plt.pie(x = nums, labels=labels) 69 | plt.show() 70 | 71 | # 饼图 72 | def pie_chart2(): 73 | # 数据准备 74 | data = {} 75 | data['ADC'] = 25 76 | data['APC'] = 33 77 | data['TK'] = 37 78 | data = pd.Series(data) 79 | data.plot(kind = "pie", label='heros') 80 | plt.show() 81 | 82 | # 热力图 83 | def thermodynamic(): 84 | # 数据准备 85 | np.random.seed(33) 86 | data = np.random.rand(3, 3) 87 | heatmap = sns.heatmap(data) 88 | plt.show() 89 | 90 | # 蜘蛛图 91 | def spider_chart(): 92 | # 数据准备 93 | labels=np.array([u"推进","KDA",u"生存",u"团战",u"发育",u"输出"]) 94 | stats=[76, 58, 67, 97, 86, 58] 95 | # 画图数据准备，角度、状态值 96 | angles=np.linspace(0, 2*np.pi, len(labels), endpoint=False) 97 | stats=np.concatenate((stats,[stats[0]])) 98 | angles=np.concatenate((angles,[angles[0]])) 99 | # 用Matplotlib画蜘蛛图 100 | fig = plt.figure() 101 | ax = fig.add_subplot(111, polar=True) 102 | ax.plot(angles, stats, 'o-', linewidth=2) 103 | ax.fill(angles, stats, alpha=0.25) 104 | # 设置中文字体 105 | font = FontProperties(fname=r"C:\Windows\Fonts\simhei.ttf", size=14) 106 | ax.set_thetagrids(angles * 180/np.pi, labels, FontProperties=font) 107 | plt.show() 108 | 109 | # 二元变量分布图 110 | def jointplot(): 111 | # 数据准备 112 | flights = sns.load_dataset("flights") 113 | # 用Seaborn画二元变量分布图（散点图，核密度图，Hexbin图） 114 | sns.jointplot(x="year", y="passengers", data=flights, kind='scatter') 115 | sns.jointplot(x="year", y="passengers", data=flights, kind='kde') 116 | sns.jointplot(x="year", y="passengers", data=flights, kind='hex') 117 | plt.show() 118 | 119 | # 成对关系图 120 | def pairplot(): 121 | # 数据准备 122 | flights = sns.load_dataset('flights') 123 | # 用Seaborn画成对关系 124 | sns.pairplot(flights) 125 | plt.show() 126 | 127 | def thermodynamic2(): 128 | flights = sns.load_dataset('flights') 129 | print(flights) 130 | flights=flights.pivot('month','year','passengers') #pivot函数重要 131 | print(flights) 132 | sns.heatmap(flights) #注意这里是直接传入数据集即可，不需要再单独传入x和y了 133 | sns.heatmap(flights,linewidth=.5,annot=True,fmt='d') 134 | plt.show() 135 | 136 | 137 | # 散点图 138 | #scatter() 139 | # 折线图 140 | #line_chart() 141 | # 条形图 142 | bar_chart() 143 | # 箱线图 144 | #box_plots() 145 | # 饼图 146 | #pie_chart() 147 | #pie_chart2() 148 | # 热力图 149 | #thermodynamic() 150 | #thermodynamic2() 151 | # 蜘蛛图 152 | #spider_chart() 153 | # 二元变量分布图 154 | #jointplot() 155 | # 成对关系图 156 | #pairplot() -------------------------------------------------------------------------------- /L3/PythonEDA/subplot1.py: -------------------------------------------------------------------------------- 1 | # subplot使用 2 | import matplotlib.pyplot as plt 3 | import numpy as np 4 | 5 | def f(t): 6 | return np.exp(-t) * np.cos(2 * np.pi * t) 7 | 8 | t1 = np.arange(0, 5, 0.1) 9 | t2 = np.arange(0, 5, 0.02) 10 | 11 | plt.figure() 12 | plt.subplot(221) 13 | plt.plot(t1, f(t1), 'r--') 14 | 15 | plt.subplot(222) 16 | plt.plot(t2, np.cos(2 * np.pi * t2), 'r--') 17 | 18 | plt.subplot(212) 19 | plt.plot([1, 2, 3, 4], [1, 4, 9, 16]) 20 | 21 | plt.show() -------------------------------------------------------------------------------- /L3/PythonEDA/titanic_eda.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | import pandas as pd 3 | from sklearn.tree import DecisionTreeClassifier 4 | from sklearn.feature_extraction import DictVectorizer 5 | from sklearn.model_selection import cross_val_score 6 | from sklearn import metrics 7 | from sklearn.feature_extraction import DictVectorizer 8 | import matplotlib.pyplot as plt 9 | import seaborn as sns 10 | 11 | # 数据加载 12 | train_data = pd.read_csv('./train.csv') 13 | test_data = pd.read_csv('./test.csv') 14 | # 使用平均年龄来填充年龄中的nan值 15 | train_data['Age'].fillna(train_data['Age'].mean(), inplace=True) 16 | test_data['Age'].fillna(test_data['Age'].mean(),inplace=True) 17 | # 使用票价的均值填充票价中的nan值 18 | train_data['Fare'].fillna(train_data['Fare'].mean(), inplace=True) 19 | test_data['Fare'].fillna(test_data['Fare'].mean(),inplace=True) 20 | #print(train_data['Embarked'].value_counts()) 21 | # 使用登录最多的港口来填充登录港口的nan值 22 | train_data['Embarked'].fillna('S', inplace=True) 23 | test_data['Embarked'].fillna('S',inplace=True) 24 | # 特征选择 25 | features = ['Pclass', 'Sex', 'Age', 'SibSp', 'Parch', 'Fare', 'Embarked'] 26 | train_features = train_data[features] 27 | 28 | # 显示特征之间的相关系数 29 | plt.figure(figsize=(10, 10)) 30 | plt.title('Pearson Correlation between Features',y=1.05,size=15) 31 | train_data_hot_encoded = train_features.drop('Embarked',1).join(train_features.Embarked.str.get_dummies()) 32 | train_data_hot_encoded = train_data_hot_encoded.drop('Sex',1).join(train_data_hot_encoded.Sex.str.get_dummies()) 33 | # 计算特征之间的Pearson系数，即相似度 34 | sns.heatmap(train_data_hot_encoded.corr(),linewidths=0.1,vmax=1.0, fmt= '.2f', square=True,linecolor='white',annot=True) 35 | plt.show() 36 | 37 | 38 | # 使用饼图来进行Survived取值的可视化 39 | #print(type(train_data["Survived"].value_counts())) 40 | train_data["Survived"].value_counts().plot(kind = "pie", label='Survived') 41 | plt.show() 42 | 43 | # 不同的Pclass,幸存人数(条形图) 44 | sns.barplot(x = 'Pclass', y = "Survived", data = train_data); 45 | plt.show() 46 | 47 | # 不同的Embarked,幸存人数(条形图) 48 | sns.barplot(x = 'Embarked', y = "Survived", data = train_data); 49 | plt.show() 50 | 51 | 52 | # 训练并显示特征向量的重要程度 53 | def train(train_features, train_labels): 54 | # 构造CART决策树 55 | clf = DecisionTreeClassifier() 56 | # 决策树训练 57 | clf.fit(train_features, train_labels) 58 | # 显示特征向量的重要程度 59 | coeffs = clf.feature_importances_ 60 | #print(coeffs) 61 | df_co = pd.DataFrame(coeffs, columns=["importance_"]) 62 | # 下标设置为Feature Name 63 | df_co.index = train_features.columns 64 | #print(df_co.index) 65 | df_co.sort_values("importance_", ascending=True, inplace=True) 66 | df_co.importance_.plot(kind="barh") 67 | 68 | plt.title("Feature Importance") 69 | plt.show() 70 | return clf 71 | 72 | clf = train(train_data_hot_encoded, train_data["Survived"]) 73 | 74 | # 决策树可视化 75 | import pydotplus 76 | from sklearn.externals.six import StringIO 77 | from sklearn.tree import export_graphviz 78 | 79 | def show_tree(clf): 80 | dot_data = StringIO() 81 | export_graphviz(clf, out_file=dot_data) 82 | graph = pydotplus.graph_from_dot_data(dot_data.getvalue()) 83 | graph.write_pdf("titanic_tree.pdf") 84 | 85 | show_tree(clf) -------------------------------------------------------------------------------- /L3/echarts/bar1.html: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | ECharts 条形图 6 | 7 | 8 | 9 | 10 | 11 |
12 | 39 | 40 | -------------------------------------------------------------------------------- /L3/echarts/bar1.py: -------------------------------------------------------------------------------- 1 | # 柱状图绘制 2 | import pyecharts.options as opts 3 | from pyecharts.charts import Bar 4 | 5 | # 绘制单列柱状图 6 | def work1(): 7 | country = ["美国","西班牙","意大利","法国","德国","伊朗","英国","以色列","荷兰","奥地利"] 8 | data = [13981, 7457, 5210, 2933, 1970, 1700, 1452, 1000, 852, 684] 9 | bar = ( 10 | Bar() 11 | .add_xaxis(country) 12 | .add_yaxis("新增确诊", data) 13 | .set_series_opts(label_opts=opts.LabelOpts(is_show=False)) 14 | .set_global_opts(title_opts=opts.TitleOpts(title="昨日新增确诊国家 Top10")) 15 | ) 16 | bar.render('temp.html') 17 | #bar.render_notebook() 18 | 19 | # 绘制多列柱状图 20 | def work2(): 21 | # 绘制多列柱状图 22 | country = ["美国","西班牙","意大利","法国","德国","伊朗","英国","以色列","荷兰","奥地利"] 23 | data1 = [69223, 49515, 74386, 25233, 37323, 27017, 9529, 2369, 6412, 5560] 24 | data2 = [13981, 7457, 5210, 2933, 1970, 1700, 1452, 1000, 852, 684] 25 | bar = ( 26 | Bar() 27 | .add_xaxis(country) 28 | .add_yaxis("累计确诊", data1) 29 | .add_yaxis("新增确诊", data2) 30 | .set_series_opts(label_opts=opts.LabelOpts(is_show=False)) 31 | .set_global_opts(title_opts=opts.TitleOpts(title="昨日新增确诊国家 Top10")) 32 | ) 33 | bar.render('temp.html') 34 | 35 | #work1() 36 | work2() 37 | 38 | 39 | -------------------------------------------------------------------------------- /L3/echarts/line.py: -------------------------------------------------------------------------------- 1 | import pyecharts.options as opts 2 | from pyecharts.charts import Line 3 | 4 | # 设置折线图 5 | line=Line() 6 | # 设置x轴数据 7 | line.add_xaxis(["201{}年/{}季度".format(y,z) 8 | for y in range(4) 9 | for z in range(1,5)]) 10 | # 设置y轴数据 11 | line.add_yaxis( 12 | "手机销量", 13 | [4.80,4.10,6.00,6.50,5.80,5.20,6.80,7.40, 14 | 6.00,5.60,7.50,7.80,6.30,5.90,8.00,8.40] 15 | ) 16 | line.set_global_opts( 17 | #设置x轴标签旋转角度 18 | xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=-40),), 19 | #设置y轴名称 20 | yaxis_opts=opts.AxisOpts(name="销量（单位/百万台）"), 21 | #设置图表标题 22 | title_opts=opts.TitleOpts(title="折线图")) 23 | 24 | #渲染图表 25 | line.render_notebook() -------------------------------------------------------------------------------- /L3/echarts/page.py: -------------------------------------------------------------------------------- 1 | # 多图表page 2 | import pyecharts.options as opts 3 | from pyecharts.charts import Bar 4 | 5 | # 多page 6 | from pyecharts.charts import Page,Bar,Funnel 7 | 8 | page=Page() 9 | bar=Bar("商品销量","各季度的商品销量") 10 | bar.add("2018Q3",["轴承","弹簧","齿轮","导轨","丝杠"],[25,23,17,14,17]) 11 | bar.add("2018Q4",["轴承","弹簧","齿轮","导轨","丝杠"],[23,21,19,19,13]) 12 | page.add_chart(bar,name="bar") 13 | funnel=Funnel("订单转化效率","今日用户的订单转化效率") 14 | funnel.add("",["访问","搜索","点击","加购","订单"],[100.00,78.12,35.74,17.17,2.62]) 15 | page.add_chart(funnel,name="funnel") 16 | page.render("page.html") 17 | 18 | -------------------------------------------------------------------------------- /L3/echarts/pie.py: -------------------------------------------------------------------------------- 1 | # 绘制饼图 2 | from pyecharts import options as opts 3 | from pyecharts.charts import Page, Pie 4 | v1=["啤酒","可乐","雪碧","咖啡","奶茶"] 5 | v2=[30,19,21,12,18] 6 | 7 | pie = ( 8 | Pie() 9 | .add("", [list(z) for z in zip(v1,v2)]) 10 | .set_global_opts(title_opts=opts.TitleOpts(title="销售收入占比")) 11 | .set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {c}%"))#格式化标签输出内容 12 | ) 13 | pie.render_notebook() -------------------------------------------------------------------------------- /L3/echarts/radar.py: -------------------------------------------------------------------------------- 1 | # 绘制雷达图 2 | from pyecharts import options as opts 3 | from pyecharts.charts import Page, Radar 4 | 5 | v1 = [[4300, 10000, 28000, 35000, 50000, 19000]] 6 | v2 = [[5000, 14000, 28000, 31000, 42000, 21000]] 7 | 8 | radar = ( 9 | Radar() 10 | .add_schema( 11 | schema=[ 12 | opts.RadarIndicatorItem(name="KDA", max_=6500), 13 | opts.RadarIndicatorItem(name="输出", max_=16000), 14 | opts.RadarIndicatorItem(name="经济", max_=30000), 15 | opts.RadarIndicatorItem(name="生存", max_=38000), 16 | opts.RadarIndicatorItem(name="推进", max_=52000), 17 | opts.RadarIndicatorItem(name="打野", max_=25000), 18 | ] 19 | ) 20 | .add("鲁班", v1, #添加系列名称及数据 21 | color="red", #设置边框线的颜色 22 | areastyle_opts = opts.AreaStyleOpts(#设置填充的属性 23 | opacity = 0.5, #透明度 24 | color="red" #填充颜色 25 | ),) 26 | .add("后裔", v2,color="blue", 27 | areastyle_opts = opts.AreaStyleOpts( 28 | opacity = 0.5,#透明度 29 | color="blue" 30 | ),) 31 | .set_series_opts(label_opts=opts.LabelOpts(is_show=False)) 32 | .set_global_opts(title_opts=opts.TitleOpts(title="英雄成长对比")) 33 | ) 34 | 35 | radar.render_notebook() -------------------------------------------------------------------------------- /L3/echarts/render.html: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | Awesome-pyecharts 6 | 7 | 8 | 9 | 10 |
11 | 194 | 195 | 196 | -------------------------------------------------------------------------------- /L3/echarts/rose.py: -------------------------------------------------------------------------------- 1 | import pyecharts.options as opts 2 | from pyecharts.charts import Pie 3 | 4 | # 绘制玫瑰图 5 | rose = ( 6 | Pie() 7 | .add( 8 | "", 9 | [list(z) for z in zip(["201{}年/{}季度".format(y,z) 10 | for y in range(2) 11 | for z in range(1,3)], [4.80,4.10,5.80,5.20])], 12 | #设置内径外径 13 | radius=["0%", "75%"], 14 | #玫瑰图有两种类型 15 | rosetype="radius", 16 | label_opts=opts.LabelOpts(is_show=True), 17 | ) 18 | .set_global_opts(title_opts=opts.TitleOpts(title="Pie-玫瑰图示例")) 19 | ) 20 | rose.render_notebook() -------------------------------------------------------------------------------- /L3/echarts/temp.html: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | Awesome-pyecharts 6 | 7 | 8 | 9 | 10 |
11 | 204 | 205 | 206 | -------------------------------------------------------------------------------- /L3/feiyan_data/download_dxy_foreign_data_csv.py: -------------------------------------------------------------------------------- 1 | """ 2 | 从丁香园接口获取整体数据 3 | 国外的时序数据（没有精确到具体城市） 4 | """ 5 | import requests 6 | import json 7 | import time 8 | import pandas as pd 9 | 10 | # 获取HTML文本 11 | def get_html_text(url): 12 | for i in range(5): 13 | try: 14 | res = requests.get(url,timeout = 10) 15 | res.raise_for_status() 16 | res.encoding = res.apparent_encoding 17 | return res.text 18 | except: 19 | print('发现错误，等待1秒 继续重试') 20 | time.sleep(1) 21 | return "Error" 22 | 23 | # 将timestamp转换为日期类型 24 | def timestamp_to_date(timestamp, format_string="%Y-%m-%d"): 25 | time_array = time.localtime(timestamp) 26 | str_date = time.strftime(format_string, time_array) 27 | return str_date 28 | 29 | # 从row中得到数据 30 | def get_data_from_row(row, province, city, updateTime): 31 | confirmedCount = row['confirmedCount'] 32 | confirmedCount = row['confirmedCount'] 33 | suspectedCount = row['suspectedCount'] 34 | curedCount = row['curedCount'] 35 | deadCount = row['deadCount'] 36 | temp_dict = {'province': province, 'city': city, 'updateTime': updateTime, 'confirmedCount': confirmedCount, 'suspectedCount': suspectedCount, 'curedCount': curedCount, 'deadCount': deadCount} 37 | return temp_dict 38 | 39 | # 返回某个省份下面所有城市的数据 40 | def get_data_from_cities(results, province, updateTime): 41 | data = [] 42 | for row in results: 43 | print(row) 44 | cityName = row['cityName'] 45 | temp_dict = get_data_from_row(row, province, cityName, updateTime) 46 | data.append(temp_dict) 47 | return data 48 | 49 | # 得到指定的省份数据 50 | def get_data_from_country(country='中国'): 51 | if country == '中国': 52 | page_url = "https://lab.isaaclin.cn/nCoV/api/overall?latest=0" 53 | else: 54 | page_url = 'https://lab.isaaclin.cn/nCoV/api/area?latest=0&province=' + country 55 | 56 | data = [] 57 | text = get_html_text(page_url) 58 | results = json.loads(text)["results"] 59 | for row in results: 60 | if 'updateTime' in row: 61 | updateTime = timestamp_to_date(row['updateTime'] / 1000) 62 | else: 63 | updateTime = timestamp_to_date(row['modifyTime'] / 1000) 64 | if 'currentConfirmedCount' in row: 65 | currentConfirmedCount = row['currentConfirmedCount'] 66 | else: 67 | currentConfirmedCount = 0 68 | temp_dict = {'country': country, 'updateTime': updateTime, 'currentConfirmedCount': currentConfirmedCount, 'confirmedCount': row['confirmedCount'], 'suspectedCount': row['suspectedCount'], \ 69 | 'curedCount': row['curedCount'], 'deadCount': row['deadCount']} 70 | data.append(temp_dict) 71 | #print(row) 72 | 73 | df = pd.DataFrame(data) 74 | # 数据清洗，每个国家每天只保留最新的数据 75 | clean_df = df.drop_duplicates(['country', 'updateTime'], keep = 'first') 76 | print(clean_df) 77 | return clean_df 78 | 79 | # 从API中获取省份列表province_list 80 | def get_foreign_name(): 81 | #获取Json 82 | page_url = "https://lab.isaaclin.cn/nCoV/api/provinceName" 83 | text = get_html_text(page_url) 84 | all_list = set(json.loads(text)["results"]) 85 | # 国外的名称 = 所有国家 - 中国省份 86 | china_city = set(["上海市", "云南省", "内蒙古自治区", "北京市", "台湾", "吉林省", "四川省", "天津市", "宁夏回族自治区", "安徽省", "山东省", "山西省", "广东省", "广西壮族自治区", "新疆维吾尔自治区", "江苏省", "江西省", "河北省", "河南省", "浙江省", "湖北省", "湖南省", "澳门", "甘肃省", "福建省", "西藏自治区", "贵州省", "辽宁省", "重庆市", "陕西省", "青海省", "香港", "黑龙江省"]) 87 | foreign_list = all_list - china_city 88 | return foreign_list 89 | 90 | # 从API中获取国外国家列名 91 | foreign_list = get_foreign_name() 92 | 93 | # 得到中国的总统计数据 94 | result = get_data_from_country('中国') 95 | # 得到国外的总统计数据 96 | for country in foreign_list: 97 | df = get_data_from_country(country) 98 | #print(df) 99 | result = pd.concat([result, df]) 100 | # 保存为csv 101 | result.to_csv('./country_data.csv', index=False) 102 | 103 | 104 | -------------------------------------------------------------------------------- /L3/feiyan_data/download_qq_foreign_data_csv.py: -------------------------------------------------------------------------------- 1 | """ 2 | 从腾讯新闻接口获取当天数据 3 | 下载国外数据（国家每个城市的 最新数据，非时序） 4 | """ 5 | import requests 6 | import json 7 | import pandas as pd 8 | 9 | # 获取HTML文本 10 | def get_html_text(url): 11 | for i in range(5): 12 | try: 13 | res = requests.get(url,timeout = 10) 14 | res.raise_for_status() 15 | res.encoding = res.apparent_encoding 16 | return res.text 17 | except: 18 | print('发现错误，等待1秒 继续重试') 19 | time.sleep(1) 20 | return "Error" 21 | 22 | # 解析该国家的疫情数据 23 | def parse_children(country, children): 24 | result = [] 25 | for row in children: 26 | if 'nameMap' in row: 27 | nameMap = row['nameMap'] 28 | else: 29 | nameMap = '' 30 | temp = {'country': country, 'name':row['name'], 'nameMap':nameMap, 'confirmAdd':row['confirmAdd'], 'confirmAddCut':row['confirmAddCut'], \ 31 | 'confirm':row['confirm'],'suspect':row['suspect'], 'dead':row['dead'], 'heal':row['heal']} 32 | result.append(temp) 33 | return pd.DataFrame(result) 34 | 35 | # 腾讯新闻对应的API地址 36 | page_url = "https://view.inews.qq.com/g2/getOnsInfo?name=disease_other" 37 | #获取Json 38 | text = get_html_text(page_url) 39 | #将json数据中的data字段的数据提取处理 40 | json_text = json.loads(text)["data"] 41 | #将提取出的字符串转换为json数据 42 | json_text = json.loads(json_text) 43 | 44 | foreign_data = json_text["foreignList"] 45 | # 需要抓取的国外国家 46 | foreign_country = ['韩国', '日本本土', '意大利'] 47 | 48 | result = [] 49 | for row in foreign_data: 50 | if row['name'] in foreign_country: 51 | df = parse_children(row['name'], row['children']) 52 | if len(result) == 0: 53 | result = df 54 | else: 55 | result = pd.concat([result, df]) 56 | 57 | result.to_csv('foreign_country_data.csv', index=False) 58 | -------------------------------------------------------------------------------- /L3/feiyan_data/foreign_country_data.csv: -------------------------------------------------------------------------------- 1 | confirm,confirmAdd,confirmAddCut,country,dead,heal,name,nameMap,suspect 2 | 4326,320,0,韩国,14,4,大邱,Daegu,0 3 | 861,87,0,韩国,8,0,庆尚北道,North Gyeongsang,0 4 | 110,9,0,韩国,1,8,京畿道,Gyeonggi,0 5 | 103,4,0,韩国,0,11,首尔,Seoul,0 6 | 92,0,1,韩国,0,0,釜山,Busan,0 7 | 86,4,0,韩国,0,0,忠清南道,South Chungcheong,0 8 | 74,9,0,韩国,0,0,庆尚南道,South Gyeongsang,0 9 | 23,2,0,韩国,0,0,江原道,Gangwon,0 10 | 23,0,0,韩国,0,0,蔚山,Ulsan,0 11 | 16,1,0,韩国,0,0,大田,Daejeon,0 12 | 14,1,0,韩国,0,2,光州,Gwangju,0 13 | 12,1,0,韩国,0,0,忠清北道,North Chungcheong,0 14 | 9,0,0,韩国,0,1,仁川,Incheon,0 15 | 7,0,0,韩国,0,1,全罗北道,North Jeolla,0 16 | 5,0,0,韩国,0,1,全罗南道,South Jeolla,0 17 | 4,1,0,韩国,0,0,济州岛,Jeju,0 18 | 1,0,0,韩国,0,0,世宗,Sejong,0 19 | 0,0,0,韩国,16,3,地区待确认,,0 20 | 1820,0,0,意大利,73,250,伦巴第,Lombardy,0 21 | 544,0,0,意大利,22,6,艾米利亚-罗马涅,Emilia-Romagna,0 22 | 360,0,0,意大利,6,9,威尼托,Veneto,0 23 | 84,0,0,意大利,4,0,马尔凯,Marche,0 24 | 82,0,0,意大利,0,0,皮埃蒙特,Piemont,0 25 | 38,0,0,意大利,0,1,托斯卡纳,Tuscany,0 26 | 31,0,0,意大利,0,0,坎帕尼亚,Campania,0 27 | 30,0,0,意大利,0,3,拉齐奥,Lazio,0 28 | 26,0,0,意大利,1,4,利古里亚,Liguria,0 29 | 18,0,0,意大利,0,2,西西里,Sicily,0 30 | 18,0,0,意大利,0,0,弗留利-威尼斯-朱利亚,Friuli Venezia Giulia,0 31 | 9,0,0,意大利,1,1,阿普利亚,Apulia,0 32 | 9,0,0,意大利,0,0,翁布里亚,Umbria,0 33 | 7,0,0,意大利,0,0,阿布鲁佐,Abruzzo,0 34 | 5,0,0,意大利,0,0,特伦托自治,Provincia autonoma di Trento,0 35 | 3,0,0,意大利,0,0,莫利塞,Molise,0 36 | 2,0,0,意大利,0,0,撒丁岛,Sardegna,0 37 | 1,0,0,意大利,0,0,卡拉布里亚,calabria,0 38 | 1,0,0,意大利,0,0,博尔扎诺自治省,Provincia autonoma di Bolzano,0 39 | 1,0,0,意大利,0,0,巴西利卡塔,Basilicata,0 40 | 0,543,0,意大利,0,0,地区待确认,,0 41 | 0,0,0,意大利,0,0,特伦蒂诺-上阿迪杰,Trentino-Alto Adige - Südtirol,0 42 | 79,0,0,日本本土,3,0,北海道,Hokkaido,0 43 | 53,5,0,日本本土,0,32,地区待确认,,0 44 | 41,0,0,日本本土,0,0,爱知县,Aichi,0 45 | 40,0,0,日本本土,1,0,东京,Tokyo,0 46 | 32,0,0,日本本土,1,0,神奈川县,Kanagawa,0 47 | 17,0,0,日本本土,0,0,千叶县,Chiba,0 48 | 13,0,0,日本本土,1,0,和歌山县,Wakayama,0 49 | 8,0,0,日本本土,0,0,大阪府,Osaka,0 50 | 6,0,0,日本本土,0,0,石川县,Ishikawa,0 51 | 5,0,0,日本本土,0,0,熊本县,Kumamoto,0 52 | 5,0,0,日本本土,0,0,新潟县,Niigata,0 53 | 4,0,0,日本本土,0,0,埼玉县,Saitama,0 54 | 3,0,0,日本本土,0,0,京都府,Kyoto,0 55 | 3,0,0,日本本土,0,0,高知县,Kochi,0 56 | 3,0,0,日本本土,0,0,兵库县,Hyogo,0 57 | 3,0,0,日本本土,0,0,冲绳县,Okinawa,0 58 | 3,0,0,日本本土,0,0,福冈县,Fukuoka,0 59 | 2,0,0,日本本土,0,0,长野县,Nagano,0 60 | 2,0,0,日本本土,0,0,岐阜县,Nagano,0 61 | 1,0,0,日本本土,0,0,静冈县,Shizuoka,0 62 | 1,0,0,日本本土,0,0,栃木县,Tochigi,0 63 | 1,0,0,日本本土,0,0,宫城县,Miyagi,0 64 | 1,0,0,日本本土,0,0,爱媛县,Ehime,0 65 | 1,0,0,日本本土,0,0,山口县,Yamaguchi,0 66 | 1,0,0,日本本土,0,0,大分县,oita,0 67 | 1,0,0,日本本土,0,0,德岛县,Tokushima,0 68 | 1,0,0,日本本土,0,0,奈良县,Nara,0 69 | 1,0,0,日本本土,0,0,三重县,Mie,0 70 | -------------------------------------------------------------------------------- /L3/feiyan_flask/App/__init__.py: -------------------------------------------------------------------------------- 1 | from flask import Flask 2 | 3 | from App.ext import init_ext 4 | from App.views import init_blue 5 | 6 | def create_app(): 7 | 8 | app = Flask(__name__) 9 | # 初始化app 10 | # 配置flask配置对象中键：SQLALCHEMY_DATABASE_URI 11 | 12 | app.config['SQLALCHEMY_DATABASE_URI'] = "mysql+pymysql://wucai:wucai1234!@rm-uf6z891lon6dxuqblqo.mysql.rds.aliyuncs.com:3306/nba_data" 13 | # 14 | 15 | 16 | # 配置flask配置对象中键：SQLALCHEMY_COMMIT_TEARDOWN,设置为True,应用会自动在每次请求结束后提交数据库中变动 17 | app.config['SECRET_KEY'] = '123456' 18 | app.config['SQLALCHEMY_COMMIT_TEARDOWN'] = True 19 | app.config['SQLALCHEMY_TRACK_MODIFICATIONS'] = True 20 | app.config['SQLALCHEMY_COMMIT_ON_TEARDOWN'] = True 21 | 22 | 23 | # 初始化蓝图，路由 24 | init_blue(app) 25 | 26 | # 初始化第三方库 27 | init_ext(app) 28 | return app 29 | 30 | 31 | 32 | -------------------------------------------------------------------------------- /L3/feiyan_flask/App/__pycache__/__init__.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cystanford/Data_Analysis_with_Python/a33b965d98612031a0effe17a9c6da3a1eaefb5e/L3/feiyan_flask/App/__pycache__/__init__.cpython-36.pyc -------------------------------------------------------------------------------- /L3/feiyan_flask/App/__pycache__/__init__.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cystanford/Data_Analysis_with_Python/a33b965d98612031a0effe17a9c6da3a1eaefb5e/L3/feiyan_flask/App/__pycache__/__init__.cpython-37.pyc -------------------------------------------------------------------------------- /L3/feiyan_flask/App/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cystanford/Data_Analysis_with_Python/a33b965d98612031a0effe17a9c6da3a1eaefb5e/L3/feiyan_flask/App/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /L3/feiyan_flask/App/__pycache__/ext.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cystanford/Data_Analysis_with_Python/a33b965d98612031a0effe17a9c6da3a1eaefb5e/L3/feiyan_flask/App/__pycache__/ext.cpython-36.pyc -------------------------------------------------------------------------------- /L3/feiyan_flask/App/__pycache__/ext.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cystanford/Data_Analysis_with_Python/a33b965d98612031a0effe17a9c6da3a1eaefb5e/L3/feiyan_flask/App/__pycache__/ext.cpython-37.pyc -------------------------------------------------------------------------------- /L3/feiyan_flask/App/__pycache__/ext.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cystanford/Data_Analysis_with_Python/a33b965d98612031a0effe17a9c6da3a1eaefb5e/L3/feiyan_flask/App/__pycache__/ext.cpython-38.pyc -------------------------------------------------------------------------------- /L3/feiyan_flask/App/__pycache__/models.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cystanford/Data_Analysis_with_Python/a33b965d98612031a0effe17a9c6da3a1eaefb5e/L3/feiyan_flask/App/__pycache__/models.cpython-36.pyc -------------------------------------------------------------------------------- /L3/feiyan_flask/App/__pycache__/models.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cystanford/Data_Analysis_with_Python/a33b965d98612031a0effe17a9c6da3a1eaefb5e/L3/feiyan_flask/App/__pycache__/models.cpython-37.pyc -------------------------------------------------------------------------------- /L3/feiyan_flask/App/ext.py: -------------------------------------------------------------------------------- 1 | from flask_migrate import Migrate 2 | from flask_sqlalchemy import SQLAlchemy 3 | 4 | 5 | db = SQLAlchemy() 6 | migrate = Migrate() 7 | 8 | 9 | def init_ext(app): 10 | 11 | db.init_app(app) 12 | migrate.init_app(app=app, db=db) -------------------------------------------------------------------------------- /L3/feiyan_flask/App/models.py: -------------------------------------------------------------------------------- 1 | # coding: utf-8 2 | from sqlalchemy import Column, DateTime, Float, Index, String, Table 3 | from sqlalchemy.dialects.mysql import BIGINT, INTEGER, TINYINT, VARCHAR,DATETIME 4 | from sqlalchemy.ext.declarative import declarative_base 5 | from .ext import db 6 | Base = declarative_base() 7 | metadata = Base.metadata 8 | 9 | 10 | -------------------------------------------------------------------------------- /L3/feiyan_flask/App/static/js/axis.js: -------------------------------------------------------------------------------- 1 | //温度统计曲线图 2 | function echartsColumnarAxis(id) { 3 | // 初始化echart实例，获取dom 4 | let dom = echarts.init(document.getElementById(id)); 5 | console.log() 6 | //下面是配置 7 | var option = { 8 | tooltip: { 9 | trigger: 'axis', 10 | axisPointer: { 11 | type: 'shadow' 12 | } 13 | }, 14 | legend: { 15 | data: ['当前人数占比', '对比全网人群', '负面占比'], 16 | show: false 17 | }, 18 | grid: { 19 | left: '3%', 20 | right: '4%', 21 | bottom: '3%', 22 | top: '5%', 23 | containLabel: true 24 | }, 25 | xAxis: { 26 | type: 'value', 27 | axisTick: { 28 | show: false, 29 | }, 30 | triggerEvent: false, 31 | axisLine: { 32 | show: false 33 | }, 34 | axisLabel: { 35 | show: false, 36 | } 37 | }, 38 | yAxis: { 39 | type: 'category', 40 | scale: false, 41 | axisLine: { 42 | show: false 43 | }, 44 | axisTick: { 45 | show: false 46 | }, 47 | axisLabel: { 48 | show: true, 49 | textStyle: { 50 | color: '#687284' 51 | }, 52 | }, 53 | splitLine: { 54 | show: false, 55 | }, 56 | data: ['单身', '恋爱', '准备结婚', '已婚未孕', '育婴', '已婚已育', '孝敬期'].reverse(), 57 | 58 | }, 59 | series: [{ 60 | name: '当前人数占比', 61 | type: 'bar', 62 | data: [20, 21, 22, 25, 27, 22, 20], 63 | color: '#1d428a' 64 | }, 65 | { 66 | name: '对比全网人群', 67 | type: 'bar', 68 | data: [20, 21, 22, 25, 27, 99, 20], 69 | color: '#ff9d00' 70 | }, 71 | { 72 | name: '负面占比', 73 | type: 'bar', 74 | data: [20, 21, 22, 25, 27, 0, 20, 21, 22, 25, 27, 0], 75 | color: '#97d2fe' 76 | } 77 | ] 78 | } 79 | //使用刚指定的配置项和数据显示图表 80 | dom.setOption(option); 81 | } -------------------------------------------------------------------------------- /L3/feiyan_flask/App/static/js/map.js: -------------------------------------------------------------------------------- 1 | //世界地图 2 | function echartsWorld(scales, data) { 3 | var mapName = 'world' 4 | //console.log(data); 5 | let scales1 = echarts.init(document.getElementById(scales)); 6 | var option = { 7 | //滑入的弹窗 8 | tooltip: { 9 | trigger: 'item', 10 | triggerOn: 'mousemove', 11 | backgroundColor: 'rgba(0,0,0,.8)', 12 | show: true, 13 | formatter: function(params) { 14 | if (isNaN(params.value)) {params.value=0;} 15 | //console.log(params.value); 16 | var tipHtml = `
17 |
18 | ${params.name} 19 |
20 |
21 |

22 | 累计确诊： 23 | ${params.value}人

24 |
25 |
26 | ` 27 | return tipHtml; 28 | } 29 | }, 30 | backgroundColor: "#ffffff", 31 | visualMap: { 32 | type: 'piecewise', 33 | // 根据数据大小跳转颜色 34 | pieces: [{max: 0,label: '0人',color: '#A9A9A9'}, // 灰色 35 | {min: 1, max: 9,label: '1-9人',color: '#FFD194'}, 36 | {min: 10, max: 99,label: '1-9人',color: '#FFC085'}, 37 | {min: 100, max: 499, label: '100-499人',color: '#FFA769'}, 38 | {min: 500, max: 999, label: '500-999人',color: '#FF8E59'}, 39 | {min: 1000, max: 9999, label: '1000-9999人',color: '#FF7859'}, 40 | {min: 10000,label: '10000人以上',color: '#FF6250'}, 41 | ], 42 | color: '#000', 43 | textStyle: { 44 | color: '#000', 45 | }, 46 | visibility: 'off' 47 | }, 48 | geo: { 49 | map: 'world', 50 | zoom: 1.2, 51 | roam: false, 52 | label: { 53 | normal: { 54 | show: false, 55 | color: '#fff' 56 | }, 57 | emphasis: { 58 | show: true, 59 | color: '#fff' 60 | } 61 | }, 62 | itemStyle: { 63 | normal: { 64 | areaColor: '#A9A9A9', 65 | borderColor: '#fff', 66 | }, 67 | emphasis: { 68 | areaColor: '#FA8072' 69 | } 70 | } 71 | }, 72 | series: [{ 73 | type: 'map', 74 | mapType: 'world', 75 | geoIndex: 0, 76 | data: data, 77 | label: { 78 | normal: { 79 | show: true, 80 | textStyle: { 81 | color: '#000', 82 | fontSize: 11, 83 | } 84 | } 85 | }, 86 | zlevel: 5, 87 | }, ] 88 | }; 89 | scales1.setOption(option); 90 | } 91 | 92 | // 韩国地图 93 | function echartsKorea(scales, data) { 94 | var mapName = 'korea'; 95 | let scales1 = echarts.init(document.getElementById(scales)); 96 | //console.log(scales1); 97 | 98 | var option = { 99 | //滑入的弹窗 100 | tooltip: { 101 | trigger: 'item', 102 | triggerOn: 'mousemove', 103 | backgroundColor: 'rgba(0,0,0,.8)', 104 | show: true, 105 | formatter: function(params) { 106 | if (isNaN(params.value)) {params.value=0;} 107 | var tipHtml = `
108 |
109 | ${params.name} 110 |
111 |
112 |

113 | 累计确诊： 114 | ${params.value}人

115 |
116 |
117 | ` 118 | return tipHtml; 119 | } 120 | }, 121 | backgroundColor: "#ffffff", 122 | visualMap: { 123 | type: 'piecewise', 124 | // 根据数据大小跳转颜色 125 | pieces: [{max: 0,label: '0人',color: '#A9A9A9'}, // 灰色 126 | {min: 1, max: 9,label: '1-9人',color: '#FFD194'}, 127 | {min: 10, max: 99,label: '1-9人',color: '#FFC085'}, 128 | {min: 100, max: 499, label: '100-499人',color: '#FFA769'}, 129 | {min: 500, label: '500-999人',color: '#FF8E59'}, 130 | ], 131 | color: '#000', 132 | textStyle: { 133 | color: '#000', 134 | }, 135 | visibility: 'off' 136 | }, 137 | geo: { 138 | map: 'korea', 139 | zoom: 1.2, 140 | roam: false, 141 | label: { 142 | normal: { 143 | show: false, 144 | color: '#fff' 145 | }, 146 | emphasis: { 147 | show: true, 148 | color: '#fff' 149 | } 150 | }, 151 | itemStyle: { 152 | normal: { 153 | areaColor: '#A9A9A9', 154 | borderColor: '#fff', 155 | }, 156 | emphasis: { 157 | areaColor: '#FA8072' 158 | } 159 | } 160 | }, 161 | series: [{ 162 | type: 'map', 163 | mapType: 'korea', 164 | geoIndex: 0, 165 | data: data, 166 | label: { 167 | normal: { 168 | show: false, 169 | textStyle: { 170 | color: '#000', 171 | fontSize: 11, 172 | } 173 | } 174 | }, 175 | zlevel: 5, 176 | }, ] 177 | }; 178 | scales1.setOption(option); 179 | } 180 | 181 | // 日本地图 182 | function echartsJapan(scales, data) { 183 | var mapName = 'japan'; 184 | let scales1 = echarts.init(document.getElementById(scales)); 185 | var option = { 186 | //滑入的弹窗 187 | tooltip: { 188 | trigger: 'item', 189 | triggerOn: 'mousemove', 190 | backgroundColor: 'rgba(0,0,0,.8)', 191 | show: true, 192 | formatter: function(params) { 193 | if (isNaN(params.value)) {params.value=0;} 194 | var tipHtml = `
195 |
196 | ${params.name} 197 |
198 |
199 |

200 | 累计确诊： 201 | ${params.value}人

202 |
203 |
204 | ` 205 | return tipHtml; 206 | } 207 | }, 208 | backgroundColor: "#ffffff", 209 | visualMap: { 210 | type: 'piecewise', 211 | // 根据数据大小跳转颜色 212 | pieces: [{max: 0,label: '0人',color: '#A9A9A9'}, // 灰色 213 | {min: 1, max: 9,label: '1-9人',color: '#FFD194'}, 214 | {min: 10, max: 99,label: '1-9人',color: '#FFC085'}, 215 | {min: 100, max: 499, label: '100-499人',color: '#FFA769'}, 216 | {min: 500, label: '500-999人',color: '#FF8E59'}, 217 | ], 218 | color: '#000', 219 | textStyle: { 220 | color: '#000', 221 | }, 222 | visibility: 'off' 223 | }, 224 | geo: { 225 | map: 'japan', 226 | zoom: 1.2, 227 | roam: false, 228 | label: { 229 | normal: { 230 | show: false, 231 | color: '#fff' 232 | }, 233 | emphasis: { 234 | show: true, 235 | color: '#fff' 236 | } 237 | }, 238 | itemStyle: { 239 | normal: { 240 | areaColor: '#A9A9A9', 241 | borderColor: '#fff', 242 | }, 243 | emphasis: { 244 | areaColor: '#FA8072' 245 | } 246 | } 247 | }, 248 | series: [{ 249 | type: 'map', 250 | mapType: 'japan', 251 | geoIndex: 0, 252 | data: data, 253 | label: { 254 | normal: { 255 | show: true, 256 | textStyle: { 257 | color: '#000', 258 | fontSize: 11, 259 | } 260 | } 261 | }, 262 | zlevel: 5, 263 | }, ] 264 | }; 265 | scales1.setOption(option); 266 | } 267 | 268 | // 意大利地图 269 | function echartsItaly(scales, data) { 270 | var mapName = 'italy'; 271 | let scales1 = echarts.init(document.getElementById(scales)); 272 | var option = { 273 | //滑入的弹窗 274 | tooltip: { 275 | trigger: 'item', 276 | triggerOn: 'mousemove', 277 | backgroundColor: 'rgba(0,0,0,.8)', 278 | show: true, 279 | formatter: function(params) { 280 | if (isNaN(params.value)) {params.value=0;} 281 | var tipHtml = `
282 |
283 | ${params.name} 284 |
285 |
286 |

287 | 累计确诊： 288 | ${params.value}人

289 |
290 |
291 | ` 292 | return tipHtml; 293 | } 294 | }, 295 | backgroundColor: "#ffffff", 296 | visualMap: { 297 | type: 'piecewise', 298 | // 根据数据大小跳转颜色 299 | pieces: [{max: 0,label: '0人',color: '#A9A9A9'}, // 灰色 300 | {min: 1, max: 9,label: '1-9人',color: '#FFD194'}, 301 | {min: 10, max: 99,label: '1-9人',color: '#FFC085'}, 302 | {min: 100, max: 499, label: '100-499人',color: '#FFA769'}, 303 | {min: 500, label: '500-999人',color: '#FF8E59'}, 304 | ], 305 | color: '#000', 306 | textStyle: { 307 | color: '#000', 308 | }, 309 | visibility: 'off' 310 | }, 311 | geo: { 312 | map: 'italy', 313 | zoom: 1.2, 314 | roam: false, 315 | label: { 316 | normal: { 317 | show: false, 318 | color: '#fff' 319 | }, 320 | emphasis: { 321 | show: true, 322 | color: '#fff' 323 | } 324 | }, 325 | itemStyle: { 326 | normal: { 327 | areaColor: '#A9A9A9', 328 | borderColor: '#fff', 329 | }, 330 | emphasis: { 331 | areaColor: '#FA8072' 332 | } 333 | } 334 | }, 335 | series: [{ 336 | type: 'map', 337 | mapType: 'italy', 338 | geoIndex: 0, 339 | data: data, 340 | label: { 341 | normal: { 342 | show: true, 343 | textStyle: { 344 | color: '#000', 345 | fontSize: 11, 346 | } 347 | } 348 | }, 349 | zlevel: 5, 350 | }, ] 351 | }; 352 | scales1.setOption(option); 353 | } 354 | 355 | -------------------------------------------------------------------------------- /L3/feiyan_flask/App/static/json/name.json: -------------------------------------------------------------------------------- 1 | { 2 | "Afghanistan": "阿富汗", 3 | "Angola": "安哥拉", 4 | "Albania": "阿尔巴尼亚", 5 | "United Arab Emirates": "阿联酋", 6 | "Argentina": "阿根廷", 7 | "Armenia": "亚美尼亚", 8 | "French Southern and Antarctic Lands": "法属南半球和南极领地", 9 | "Australia": "澳大利亚", 10 | "Austria": "奥地利", 11 | "Azerbaijan": "阿塞拜疆", 12 | "Burundi": "布隆迪", 13 | "Belgium": "比利时", 14 | "Benin": "贝宁", 15 | "Burkina Faso": "布基纳法索", 16 | "Bangladesh": "孟加拉国", 17 | "Bulgaria": "保加利亚", 18 | "The Bahamas": "巴哈马", 19 | "Bosnia and Herzegovina": "波黑", 20 | "Belarus": "白俄罗斯", 21 | "Belize": "伯利兹", 22 | "Bermuda": "百慕大", 23 | "Bolivia": "玻利维亚", 24 | "Brazil": "巴西", 25 | "Brunei": "文莱", 26 | "Bhutan": "不丹", 27 | "Botswana": "博茨瓦纳", 28 | "Central African Republic": "中非共和国", 29 | "Canada": "加拿大", 30 | "Switzerland": "瑞士", 31 | "Chile": "智利", 32 | "China": "中国", 33 | "Ivory Coast": "象牙海岸", 34 | "Cameroon": "喀麦隆", 35 | "Democratic Republic of the Congo": "刚果（金）", 36 | "Republic of the Congo": "刚果（布）", 37 | "Colombia": "哥伦比亚", 38 | "Costa Rica": "哥斯达黎加", 39 | "Cuba": "古巴", 40 | "Northern Cyprus": "北塞浦路斯", 41 | "Cyprus": "塞浦路斯", 42 | "Czech Republic": "捷克", 43 | "Germany": "德国", 44 | "Djibouti": "吉布提", 45 | "Denmark": "丹麦", 46 | "Dominican Republic": "多米尼加共和国", 47 | "Algeria": "阿尔及利亚", 48 | "Ecuador": "厄瓜多尔", 49 | "Egypt": "埃及", 50 | "Eritrea": "厄立特里亚", 51 | "Spain": "西班牙", 52 | "Estonia": "爱沙尼亚", 53 | "Ethiopia": "埃塞俄比亚", 54 | "Finland": "芬兰", 55 | "Fiji": "斐", 56 | "Falkland Islands": "福克兰群岛", 57 | "France": "法国", 58 | "Gabon": "加蓬", 59 | "United Kingdom": "英国", 60 | "Georgia": "格鲁吉亚", 61 | "Ghana": "加纳", 62 | "Guinea": "几内亚", 63 | "Gambia": "冈比亚", 64 | "Guinea Bissau": "几内亚比绍", 65 | "Equatorial Guinea": "赤道几内亚", 66 | "Greece": "希腊", 67 | "Greenland": "格陵兰", 68 | "Guatemala": "危地马拉", 69 | "French Guiana": "法属圭亚那", 70 | "Guyana": "圭亚那", 71 | "Honduras": "洪都拉斯", 72 | "Croatia": "克罗地亚", 73 | "Haiti": "海地", 74 | "Hungary": "匈牙利", 75 | "Indonesia": "印度尼西亚", 76 | "India": "印度", 77 | "Ireland": "爱尔兰", 78 | "Iran": "伊朗", 79 | "Iraq": "伊拉克", 80 | "Iceland": "冰岛", 81 | "Israel": "以色列", 82 | "Italy": "意大利", 83 | "Jamaica": "牙买加", 84 | "Jordan": "约旦", 85 | "Japan": "日本", 86 | "Kazakhstan": "哈萨克斯坦", 87 | "Kenya": "肯尼亚", 88 | "Kyrgyzstan": "吉尔吉斯斯坦", 89 | "Cambodia": "柬埔寨", 90 | "South Korea": "韩国", 91 | "Kosovo": "科索沃", 92 | "Kuwait": "科威特", 93 | "Laos": "老挝", 94 | "Lebanon": "黎巴嫩", 95 | "Liberia": "利比里亚", 96 | "Libya": "利比亚", 97 | "Sri Lanka": "斯里兰卡", 98 | "Lesotho": "莱索托", 99 | "Lithuania": "立陶宛", 100 | "Luxembourg": "卢森堡", 101 | "Latvia": "拉脱维亚", 102 | "Morocco": "摩洛哥", 103 | "Moldova": "摩尔多瓦", 104 | "Madagascar": "马达加斯加", 105 | "Mexico": "墨西哥", 106 | "Macedonia": "马其顿", 107 | "Mali": "马里", 108 | "Myanmar": "缅甸", 109 | "Montenegro": "黑山", 110 | "Mongolia": "蒙古", 111 | "Mozambique": "莫桑比克", 112 | "Mauritania": "毛里塔尼亚", 113 | "Malawi": "马拉维", 114 | "Malaysia": "马来西亚", 115 | "Namibia": "纳米比亚", 116 | "New Caledonia": "新喀里多尼亚", 117 | "Niger": "尼日尔", 118 | "Nigeria": "尼日利亚", 119 | "Nicaragua": "尼加拉瓜", 120 | "Netherlands": "荷兰", 121 | "Norway": "挪威", 122 | "Nepal": "尼泊尔", 123 | "New Zealand": "新西兰", 124 | "Oman": "阿曼", 125 | "Pakistan": "巴基斯坦", 126 | "Panama": "巴拿马", 127 | "Peru": "秘鲁", 128 | "Philippines": "菲律宾", 129 | "Papua New Guinea": "巴布亚新几内亚", 130 | "Poland": "波兰", 131 | "Puerto Rico": "波多黎各", 132 | "North Korea": "朝鲜", 133 | "Portugal": "葡萄牙", 134 | "Paraguay": "巴拉圭", 135 | "Qatar": "卡塔尔", 136 | "Romania": "罗马尼亚", 137 | "Russia": "俄罗斯", 138 | "Rwanda": "卢旺达", 139 | "Western Sahara": "西撒哈拉", 140 | "Saudi Arabia": "沙特阿拉伯", 141 | "Sudan": "苏丹", 142 | "South Sudan": "南苏丹", 143 | "Senegal": "塞内加尔", 144 | "Solomon Islands": "所罗门群岛", 145 | "Sierra Leone": "塞拉利昂", 146 | "El Salvador": "萨尔瓦多", 147 | "Somaliland": "索马里兰", 148 | "Somalia": "索马里", 149 | "Republic of Serbia": "塞尔维亚", 150 | "Suriname": "苏里南", 151 | "Slovakia": "斯洛伐克", 152 | "Slovenia": "斯洛文尼亚", 153 | "Sweden": "瑞典", 154 | "Swaziland": "斯威士兰", 155 | "Syria": "叙利亚", 156 | "Chad": "乍得", 157 | "Togo": "多哥", 158 | "Thailand": "泰国", 159 | "Tajikistan": "塔吉克斯坦", 160 | "Turkmenistan": "土库曼斯坦", 161 | "East Timor": "东帝汶", 162 | "Trinidad and Tobago": "特里尼达和多巴哥", 163 | "Tunisia": "突尼斯", 164 | "Turkey": "土耳其", 165 | "United Republic of Tanzania": "坦桑尼亚", 166 | "Uganda": "乌干达", 167 | "Ukraine": "乌克兰", 168 | "Uruguay": "乌拉圭", 169 | "United States of America": "美国", 170 | "Uzbekistan": "乌兹别克斯坦", 171 | "Venezuela": "委内瑞拉", 172 | "Vietnam": "越南", 173 | "Vanuatu": "瓦努阿图", 174 | "West Bank": "西岸", 175 | "Yemen": "也门", 176 | "South Africa": "南非", 177 | "Zambia": "赞比亚", 178 | "Zimbabwe": "津巴布韦", 179 | "Singapore Rep.": "新加坡", 180 | "Dominican Rep.": "多米尼加", 181 | "Palestine": "巴勒斯坦", 182 | "Bahamas": "巴哈马", 183 | "Timor-Leste": "东帝汶", 184 | "Guinea-Bissau": "几内亚比绍", 185 | "Côte d'Ivoire": "科特迪瓦", 186 | "Siachen Glacier": "锡亚琴冰川", 187 | "Br. Indian Ocean Ter.": "英属印度洋领土", 188 | "Bosnia and Herz.": "波斯尼亚和黑塞哥维那", 189 | "Central African Rep.": "中非", 190 | "Dem. Rep. Congo": "刚果民主共和国", 191 | "Congo": "刚果", 192 | "N. Cyprus": "北塞浦路斯", 193 | "Czech Rep.": "捷克", 194 | "Eq. Guinea": "赤道几内亚", 195 | "Korea": "韩国", 196 | "Lao PDR": "老挝", 197 | "Dem. Rep. Korea": "朝鲜", 198 | "W. Sahara": "西撒哈拉", 199 | "S. Sudan": "南苏丹", 200 | "Solomon Is.": "所罗门群岛", 201 | "Serbia": "塞尔维亚", 202 | "Tanzania": "坦桑尼亚", 203 | "United States": "美国" 204 | } 205 | -------------------------------------------------------------------------------- /L3/feiyan_flask/App/templates/feiyan.html: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | 11 | 12 | 333 | 334 | 335 |
336 |
337 |
全球
338 |
韩国
339 |
日本
340 |
意大利
341 |
342 |
343 |
344 |
345 |
346 |
347 | 348 |
349 |
350 |
中国
351 |
韩国
352 |
日本
353 |
意大利
354 |
伊朗
355 |
356 |
357 |
358 |
359 |
360 |
361 | 362 | 363 | 400 | 401 | 529 | 530 | 531 | 532 | -------------------------------------------------------------------------------- /L3/feiyan_flask/App/views/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | from App.views.api import api 3 | 4 | 5 | def init_blue(app): 6 | app.register_blueprint(blueprint=api) -------------------------------------------------------------------------------- /L3/feiyan_flask/App/views/__pycache__/__init__.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cystanford/Data_Analysis_with_Python/a33b965d98612031a0effe17a9c6da3a1eaefb5e/L3/feiyan_flask/App/views/__pycache__/__init__.cpython-36.pyc -------------------------------------------------------------------------------- /L3/feiyan_flask/App/views/__pycache__/__init__.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cystanford/Data_Analysis_with_Python/a33b965d98612031a0effe17a9c6da3a1eaefb5e/L3/feiyan_flask/App/views/__pycache__/__init__.cpython-37.pyc -------------------------------------------------------------------------------- /L3/feiyan_flask/App/views/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cystanford/Data_Analysis_with_Python/a33b965d98612031a0effe17a9c6da3a1eaefb5e/L3/feiyan_flask/App/views/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /L3/feiyan_flask/App/views/__pycache__/api.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cystanford/Data_Analysis_with_Python/a33b965d98612031a0effe17a9c6da3a1eaefb5e/L3/feiyan_flask/App/views/__pycache__/api.cpython-36.pyc -------------------------------------------------------------------------------- /L3/feiyan_flask/App/views/__pycache__/api.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cystanford/Data_Analysis_with_Python/a33b965d98612031a0effe17a9c6da3a1eaefb5e/L3/feiyan_flask/App/views/__pycache__/api.cpython-37.pyc -------------------------------------------------------------------------------- /L3/feiyan_flask/App/views/api.py: -------------------------------------------------------------------------------- 1 | import pandas as pd 2 | import os 3 | from flask import Blueprint, request,render_template,redirect,json,Response 4 | from App.models import * 5 | 6 | ROOT_PATH = os.path.dirname(os.path.abspath(__file__)) 7 | api = Blueprint("api", __name__, url_prefix='/') 8 | @api.route("") 9 | def home(): 10 | return redirect("/feiyan") 11 | 12 | # 返回某个国家的疫情数据 13 | @api.route("detail_linedata/") 14 | def detailLineData(country): 15 | # 读取抓取的肺炎数据 16 | data = pd.read_csv(os.path.join(ROOT_PATH, 'country_data.csv')) 17 | nameMap = {'china': '中国', 'korea': '韩国', 'japan': '日本', 'italy': '意大利', 'iran': '伊朗'} 18 | result = data[data['country'] == nameMap[country]] 19 | result = result[['confirmedCount', 'updateTime']] 20 | # 按照时间从小到大排序 21 | result = result.sort_values(by="updateTime", ascending=True) 22 | return Response(json.dumps({'index': result['updateTime'].tolist(), 'value': result['confirmedCount'].tolist()}), content_type='application/json') 23 | 24 | 25 | # 返回某个国家的疫情数据 26 | @api.route("detaildata/") 27 | def detailData(country): 28 | # 读取抓取的肺炎数据 29 | if country == 'world': 30 | data = pd.read_csv(os.path.join(ROOT_PATH, 'country_data.csv')) 31 | data = data.drop_duplicates(['country'], keep = 'first') 32 | # 列名country => name, confirmedCount => value 33 | result = data[['country', 'confirmedCount']] 34 | result.rename(columns = {"country": "name", 'confirmedCount': 'value'}, inplace=True) 35 | else: 36 | data = pd.read_csv(os.path.join(ROOT_PATH, 'foreign_country_data.csv')) 37 | result = data[['nameMap', 'confirm']] 38 | result = result.fillna(0); 39 | #print(result) 40 | result.rename(columns = {"nameMap": "name", 'confirm': 'value'}, inplace=True) 41 | 42 | # 转换为字典列表 43 | return Response(json.dumps(result.to_dict(orient='records')), content_type='application/json') 44 | 45 | @api.route("feiyan", methods=["GET", "POST"]) 46 | def index(): 47 | # 读取抓取的肺炎数据 48 | data = pd.read_csv(os.path.join(ROOT_PATH, 'country_data.csv')) 49 | #country = data.groupby('country') 50 | country = data.drop_duplicates(['country'], keep = 'first') 51 | return render_template('feiyan.html', content=country) 52 | 53 | 54 | 55 | 56 | 57 | 58 | -------------------------------------------------------------------------------- /L3/feiyan_flask/App/views/foreign_country_data.csv: -------------------------------------------------------------------------------- 1 | confirm,confirmAdd,confirmAddCut,country,dead,heal,name,nameMap,suspect 2 | 4326,320,0,韩国,14,4,大邱,Daegu,0 3 | 861,87,0,韩国,8,0,庆尚北道,North Gyeongsang,0 4 | 110,9,0,韩国,1,8,京畿道,Gyeonggi,0 5 | 103,4,0,韩国,0,11,首尔,Seoul,0 6 | 92,0,1,韩国,0,0,釜山,Busan,0 7 | 86,4,0,韩国,0,0,忠清南道,South Chungcheong,0 8 | 74,9,0,韩国,0,0,庆尚南道,South Gyeongsang,0 9 | 23,2,0,韩国,0,0,江原道,Gangwon,0 10 | 23,0,0,韩国,0,0,蔚山,Ulsan,0 11 | 16,1,0,韩国,0,0,大田,Daejeon,0 12 | 14,1,0,韩国,0,2,光州,Gwangju,0 13 | 12,1,0,韩国,0,0,忠清北道,North Chungcheong,0 14 | 9,0,0,韩国,0,1,仁川,Incheon,0 15 | 7,0,0,韩国,0,1,全罗北道,North Jeolla,0 16 | 5,0,0,韩国,0,1,全罗南道,South Jeolla,0 17 | 4,1,0,韩国,0,0,济州岛,Jeju,0 18 | 1,0,0,韩国,0,0,世宗,Sejong,0 19 | 0,0,0,韩国,16,3,地区待确认,,0 20 | 1820,0,0,意大利,73,250,伦巴第,Lombardy,0 21 | 544,0,0,意大利,22,6,艾米利亚-罗马涅,Emilia-Romagna,0 22 | 360,0,0,意大利,6,9,威尼托,Veneto,0 23 | 84,0,0,意大利,4,0,马尔凯,Marche,0 24 | 82,0,0,意大利,0,0,皮埃蒙特,Piemont,0 25 | 38,0,0,意大利,0,1,托斯卡纳,Tuscany,0 26 | 31,0,0,意大利,0,0,坎帕尼亚,Campania,0 27 | 30,0,0,意大利,0,3,拉齐奥,Lazio,0 28 | 26,0,0,意大利,1,4,利古里亚,Liguria,0 29 | 18,0,0,意大利,0,2,西西里,Sicily,0 30 | 18,0,0,意大利,0,0,弗留利-威尼斯-朱利亚,Friuli Venezia Giulia,0 31 | 9,0,0,意大利,1,1,阿普利亚,Apulia,0 32 | 9,0,0,意大利,0,0,翁布里亚,Umbria,0 33 | 7,0,0,意大利,0,0,阿布鲁佐,Abruzzo,0 34 | 5,0,0,意大利,0,0,特伦托自治,Provincia autonoma di Trento,0 35 | 3,0,0,意大利,0,0,莫利塞,Molise,0 36 | 2,0,0,意大利,0,0,撒丁岛,Sardegna,0 37 | 1,0,0,意大利,0,0,卡拉布里亚,calabria,0 38 | 1,0,0,意大利,0,0,博尔扎诺自治省,Provincia autonoma di Bolzano,0 39 | 1,0,0,意大利,0,0,巴西利卡塔,Basilicata,0 40 | 0,543,0,意大利,0,0,地区待确认,,0 41 | 0,0,0,意大利,0,0,特伦蒂诺-上阿迪杰,Trentino-Alto Adige - Südtirol,0 42 | 79,0,0,日本本土,3,0,北海道,Hokkaido,0 43 | 53,5,0,日本本土,0,32,地区待确认,,0 44 | 41,0,0,日本本土,0,0,爱知县,Aichi,0 45 | 40,0,0,日本本土,1,0,东京,Tokyo,0 46 | 32,0,0,日本本土,1,0,神奈川县,Kanagawa,0 47 | 17,0,0,日本本土,0,0,千叶县,Chiba,0 48 | 13,0,0,日本本土,1,0,和歌山县,Wakayama,0 49 | 8,0,0,日本本土,0,0,大阪府,Osaka,0 50 | 6,0,0,日本本土,0,0,石川县,Ishikawa,0 51 | 5,0,0,日本本土,0,0,熊本县,Kumamoto,0 52 | 5,0,0,日本本土,0,0,新潟县,Niigata,0 53 | 4,0,0,日本本土,0,0,埼玉县,Saitama,0 54 | 3,0,0,日本本土,0,0,京都府,Kyoto,0 55 | 3,0,0,日本本土,0,0,高知县,Kochi,0 56 | 3,0,0,日本本土,0,0,兵库县,Hyogo,0 57 | 3,0,0,日本本土,0,0,冲绳县,Okinawa,0 58 | 3,0,0,日本本土,0,0,福冈县,Fukuoka,0 59 | 2,0,0,日本本土,0,0,长野县,Nagano,0 60 | 2,0,0,日本本土,0,0,岐阜县,Nagano,0 61 | 1,0,0,日本本土,0,0,静冈县,Shizuoka,0 62 | 1,0,0,日本本土,0,0,栃木县,Tochigi,0 63 | 1,0,0,日本本土,0,0,宫城县,Miyagi,0 64 | 1,0,0,日本本土,0,0,爱媛县,Ehime,0 65 | 1,0,0,日本本土,0,0,山口县,Yamaguchi,0 66 | 1,0,0,日本本土,0,0,大分县,oita,0 67 | 1,0,0,日本本土,0,0,德岛县,Tokushima,0 68 | 1,0,0,日本本土,0,0,奈良县,Nara,0 69 | 1,0,0,日本本土,0,0,三重县,Mie,0 70 | -------------------------------------------------------------------------------- /L3/feiyan_flask/__pycache__/manage.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cystanford/Data_Analysis_with_Python/a33b965d98612031a0effe17a9c6da3a1eaefb5e/L3/feiyan_flask/__pycache__/manage.cpython-36.pyc -------------------------------------------------------------------------------- /L3/feiyan_flask/__pycache__/manage.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cystanford/Data_Analysis_with_Python/a33b965d98612031a0effe17a9c6da3a1eaefb5e/L3/feiyan_flask/__pycache__/manage.cpython-37.pyc -------------------------------------------------------------------------------- /L3/feiyan_flask/__pycache__/manage.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cystanford/Data_Analysis_with_Python/a33b965d98612031a0effe17a9c6da3a1eaefb5e/L3/feiyan_flask/__pycache__/manage.cpython-38.pyc -------------------------------------------------------------------------------- /L3/feiyan_flask/manage.py: -------------------------------------------------------------------------------- 1 | import os 2 | from flask_migrate import MigrateCommand 3 | from flask_script import Manager 4 | 5 | 6 | from App import create_app 7 | 8 | app = create_app() 9 | app.jinja_env.auto_reload = True 10 | app.config['TEMPLATES_AUTO_RELOAD'] = True 11 | 12 | manager = Manager(app) 13 | manager.add_command("db", MigrateCommand) 14 | 15 | 16 | if __name__ == '__main__': 17 | manager.run() 18 | -------------------------------------------------------------------------------- /L3/feiyan_flask/nohup.out: -------------------------------------------------------------------------------- 1 | * Serving Flask app "App" (lazy loading) 2 | * Environment: production 3 | WARNING: This is a development server. Do not use it in a production deployment. 4 | Use a production WSGI server instead. 5 | * Debug mode: off 6 | * Running on http://0.0.0.0:80/ (Press CTRL+C to quit) 7 | 183.192.95.88 - - [19/Feb/2020 18:50:51] "GET / HTTP/1.1" 302 - 8 | /usr/local/lib/python3.7/site-packages/pymysql/cursors.py:170: Warning: (3719, "'utf8' is currently an alias for the character set UTF8MB3, but will be an alias for UTF8MB4 in a future release. Please consider using UTF8MB4 in order to be unambiguous.") 9 | result = self._query(query) 10 | 183.192.95.88 - - [19/Feb/2020 18:50:51] "GET /player/1 HTTP/1.1" 200 - 11 | 183.192.95.88 - - [19/Feb/2020 18:50:51] "GET /favicon.ico HTTP/1.1" 404 - 12 | 84.97.56.137 - - [19/Feb/2020 19:01:47] "GET / HTTP/1.1" 302 - 13 | 79.124.62.14 - - [19/Feb/2020 19:42:49] code 400, message Bad HTTP/0.9 request type ('\x03\x00\x00/*à\x00\x00\x00\x00\x00Cookie:') 14 | 79.124.62.14 - - [19/Feb/2020 19:42:49] "/*àCookie: mstshash=Administr" HTTPStatus.BAD_REQUEST - 15 | 120.55.14.213 - - [19/Feb/2020 19:55:53] "GET /examples/servlets/index.html HTTP/1.1" 404 - 16 | 120.55.14.213 - - [19/Feb/2020 19:55:53] "GET /examples/jsp/index.html HTTP/1.1" 404 - 17 | 120.55.14.213 - - [19/Feb/2020 19:55:53] "GET /examples/jsp/snp/snoop.jsp HTTP/1.1" 404 - 18 | 114.246.202.73 - - [19/Feb/2020 19:56:13] "GET / HTTP/1.1" 302 - 19 | [2020-02-19 19:56:13,333] ERROR in app: Exception on /player/1 [GET] 20 | Traceback (most recent call last): 21 | File "/usr/local/lib/python3.7/site-packages/pymysql/connections.py", line 713, in _write_bytes 22 | self._sock.sendall(data) 23 | ConnectionResetError: [Errno 104] Connection reset by peer 24 | 25 | During handling of the above exception, another exception occurred: 26 | 27 | Traceback (most recent call last): 28 | File "/usr/local/lib/python3.7/site-packages/sqlalchemy/engine/base.py", line 1246, in _execute_context 29 | cursor, statement, parameters, context 30 | File "/usr/local/lib/python3.7/site-packages/sqlalchemy/engine/default.py", line 588, in do_execute 31 | cursor.execute(statement, parameters) 32 | File "/usr/local/lib/python3.7/site-packages/pymysql/cursors.py", line 170, in execute 33 | result = self._query(query) 34 | File "/usr/local/lib/python3.7/site-packages/pymysql/cursors.py", line 328, in _query 35 | conn.query(q) 36 | File "/usr/local/lib/python3.7/site-packages/pymysql/connections.py", line 516, in query 37 | self._execute_command(COMMAND.COM_QUERY, sql) 38 | File "/usr/local/lib/python3.7/site-packages/pymysql/connections.py", line 771, in _execute_command 39 | self._write_bytes(packet) 40 | File "/usr/local/lib/python3.7/site-packages/pymysql/connections.py", line 718, in _write_bytes 41 | "MySQL server has gone away (%r)" % (e,)) 42 | pymysql.err.OperationalError: (2006, "MySQL server has gone away (ConnectionResetError(104, 'Connection reset by peer'))") 43 | 44 | The above exception was the direct cause of the following exception: 45 | 46 | Traceback (most recent call last): 47 | File "/usr/local/lib/python3.7/site-packages/flask/app.py", line 2446, in wsgi_app 48 | response = self.full_dispatch_request() 49 | File "/usr/local/lib/python3.7/site-packages/flask/app.py", line 1951, in full_dispatch_request 50 | rv = self.handle_user_exception(e) 51 | File "/usr/local/lib/python3.7/site-packages/flask/app.py", line 1820, in handle_user_exception 52 | reraise(exc_type, exc_value, tb) 53 | File "/usr/local/lib/python3.7/site-packages/flask/_compat.py", line 39, in reraise 54 | raise value 55 | File "/usr/local/lib/python3.7/site-packages/flask/app.py", line 1949, in full_dispatch_request 56 | rv = self.dispatch_request() 57 | File "/usr/local/lib/python3.7/site-packages/flask/app.py", line 1935, in dispatch_request 58 | return self.view_functions[rule.endpoint](**req.view_args) 59 | File "/home/NBA_flask/App/views/api.py", line 32, in index 60 | PlayerBasic.teamId == TeamBasic.id).order_by(PlayerBasic.lastNameEn).paginate(page=page,per_page=20) 61 | File "/usr/local/lib/python3.7/site-packages/flask_sqlalchemy/__init__.py", line 496, in paginate 62 | items = self.limit(per_page).offset((page - 1) * per_page).all() 63 | File "/usr/local/lib/python3.7/site-packages/sqlalchemy/orm/query.py", line 3233, in all 64 | return list(self) 65 | File "/usr/local/lib/python3.7/site-packages/sqlalchemy/orm/query.py", line 3389, in __iter__ 66 | return self._execute_and_instances(context) 67 | File "/usr/local/lib/python3.7/site-packages/sqlalchemy/orm/query.py", line 3414, in _execute_and_instances 68 | result = conn.execute(querycontext.statement, self._params) 69 | File "/usr/local/lib/python3.7/site-packages/sqlalchemy/engine/base.py", line 982, in execute 70 | return meth(self, multiparams, params) 71 | File "/usr/local/lib/python3.7/site-packages/sqlalchemy/sql/elements.py", line 293, in _execute_on_connection 72 | return connection._execute_clauseelement(self, multiparams, params) 73 | File "/usr/local/lib/python3.7/site-packages/sqlalchemy/engine/base.py", line 1101, in _execute_clauseelement 74 | distilled_params, 75 | File "/usr/local/lib/python3.7/site-packages/sqlalchemy/engine/base.py", line 1250, in _execute_context 76 | e, statement, parameters, cursor, context 77 | File "/usr/local/lib/python3.7/site-packages/sqlalchemy/engine/base.py", line 1476, in _handle_dbapi_exception 78 | util.raise_from_cause(sqlalchemy_exception, exc_info) 79 | File "/usr/local/lib/python3.7/site-packages/sqlalchemy/util/compat.py", line 398, in raise_from_cause 80 | reraise(type(exception), exception, tb=exc_tb, cause=cause) 81 | File "/usr/local/lib/python3.7/site-packages/sqlalchemy/util/compat.py", line 152, in reraise 82 | raise value.with_traceback(tb) 83 | File "/usr/local/lib/python3.7/site-packages/sqlalchemy/engine/base.py", line 1246, in _execute_context 84 | cursor, statement, parameters, context 85 | File "/usr/local/lib/python3.7/site-packages/sqlalchemy/engine/default.py", line 588, in do_execute 86 | cursor.execute(statement, parameters) 87 | File "/usr/local/lib/python3.7/site-packages/pymysql/cursors.py", line 170, in execute 88 | result = self._query(query) 89 | File "/usr/local/lib/python3.7/site-packages/pymysql/cursors.py", line 328, in _query 90 | conn.query(q) 91 | File "/usr/local/lib/python3.7/site-packages/pymysql/connections.py", line 516, in query 92 | self._execute_command(COMMAND.COM_QUERY, sql) 93 | File "/usr/local/lib/python3.7/site-packages/pymysql/connections.py", line 771, in _execute_command 94 | self._write_bytes(packet) 95 | File "/usr/local/lib/python3.7/site-packages/pymysql/connections.py", line 718, in _write_bytes 96 | "MySQL server has gone away (%r)" % (e,)) 97 | sqlalchemy.exc.OperationalError: (pymysql.err.OperationalError) (2006, "MySQL server has gone away (ConnectionResetError(104, 'Connection reset by peer'))") 98 | [SQL: SELECT player_basic.`playerId` AS `player_basic_playerId`, player_basic.`displayName` AS `player_basic_displayName`, player_basic.`displayNameEn` AS `player_basic_displayNameEn`, team_basic.name AS team_basic_name, player_basic.position AS player_basic_position, player_basic.weight AS player_basic_weight, player_basic.experience AS player_basic_experience, player_basic.country AS player_basic_country 99 | FROM player_basic, team_basic 100 | WHERE player_basic.`teamId` = team_basic.id ORDER BY player_basic.`lastNameEn` 101 | LIMIT %(param_1)s, %(param_2)s] 102 | [parameters: {'param_1': 0, 'param_2': 20}] 103 | (Background on this error at: http://sqlalche.me/e/e3q8) 104 | 114.246.202.73 - - [19/Feb/2020 19:56:13] "GET /player/1 HTTP/1.1" 500 - 105 | 114.246.202.73 - - [19/Feb/2020 19:56:13] "GET /favicon.ico HTTP/1.1" 404 - 106 | 114.246.202.73 - - [19/Feb/2020 19:57:31] "GET /?nsukey=0u6G0dUzNRnfbKx2e6AiVAlpJ63%2Fu1lA4k5DEKsi7YnqN0K3c8lrl%2BJyXV9oWF3dPutALJvXzbMjtEO8MTMIZuS6HmauThZqUee0iVeoZ2cv%2FkkL9qe9LBqMCJsx3uxHGFPZ0FS6imqzUCVVbbTeyQ%3D%3D HTTP/1.1" 302 - 107 | 114.246.202.73 - - [19/Feb/2020 19:57:31] "GET /player/1 HTTP/1.1" 200 - 108 | 114.246.202.73 - - [19/Feb/2020 19:57:32] "GET /player/1?nsukey=kcjwaYFnTjGgAyvcXzgZ9HWxRSy5SkbkB%2F8BWNNLP0z6ctmgeW1nIO2oy8Lw7Yqjn1clWU8%2FyImSWJS4LwAE0JDLM%2FoNf%2FwyWWTW4BgyKF36xaO8n46ChiYWcXSDCjcY2Cpb9mcuifQvje48XNWfczD8Ktg9VBOQE33erIfHBDLAWwKauCpnjvKmoIELJOBe9Vrt4D4m8Mi3GjJuhARw2A%3D%3D HTTP/1.1" 200 - 109 | 183.192.95.88 - - [19/Feb/2020 19:57:37] "GET / HTTP/1.1" 302 - 110 | 183.192.95.88 - - [19/Feb/2020 19:57:37] "GET /player/1 HTTP/1.1" 200 - 111 | 114.246.202.73 - - [19/Feb/2020 19:57:39] "GET / HTTP/1.1" 302 - 112 | 114.246.202.73 - - [19/Feb/2020 19:57:39] "GET /player/1 HTTP/1.1" 200 - 113 | 183.192.95.88 - - [19/Feb/2020 19:57:56] "GET / HTTP/1.1" 302 - 114 | 114.246.202.73 - - [19/Feb/2020 19:57:56] "GET /detail/203500 HTTP/1.1" 200 - 115 | 183.192.95.88 - - [19/Feb/2020 19:58:02] "GET / HTTP/1.1" 302 - 116 | 183.192.95.88 - - [19/Feb/2020 19:58:02] "GET /player/1 HTTP/1.1" 200 - 117 | 183.192.95.88 - - [19/Feb/2020 19:58:15] "GET /player/1 HTTP/1.1" 200 - 118 | 114.246.202.73 - - [19/Feb/2020 19:58:23] "GET /player/25 HTTP/1.1" 200 - 119 | 114.246.202.73 - - [19/Feb/2020 19:58:26] "GET /detail/1627790 HTTP/1.1" 200 - 120 | 114.246.202.73 - - [19/Feb/2020 19:58:33] "GET /player/2 HTTP/1.1" 200 - 121 | 36.107.73.70 - - [19/Feb/2020 22:17:24] "GET / HTTP/1.1" 302 - 122 | 95.133.10.181 - - [19/Feb/2020 22:48:15] "GET / HTTP/1.1" 302 - 123 | 103.68.42.135 - - [19/Feb/2020 23:29:22] "GET / HTTP/1.1" 302 - 124 | 128.14.134.170 - - [19/Feb/2020 23:55:30] "GET / HTTP/1.1" 302 - 125 | 128.14.134.170 - - [19/Feb/2020 23:55:31] "GET /player/1 HTTP/1.1" 200 - 126 | 80.82.70.187 - - [20/Feb/2020 01:00:21] "GET http://www.baidu.com/cache/global/img/gs.gif HTTP/1.1" 404 - 127 | 194.63.141.147 - - [20/Feb/2020 01:47:35] "GET / HTTP/1.1" 302 - 128 | [2020-02-20 01:47:36,638] ERROR in app: Exception on /player/1 [GET] 129 | Traceback (most recent call last): 130 | File "/usr/local/lib/python3.7/site-packages/pymysql/connections.py", line 713, in _write_bytes 131 | self._sock.sendall(data) 132 | ConnectionResetError: [Errno 104] Connection reset by peer 133 | 134 | During handling of the above exception, another exception occurred: 135 | 136 | Traceback (most recent call last): 137 | File "/usr/local/lib/python3.7/site-packages/sqlalchemy/engine/base.py", line 1246, in _execute_context 138 | cursor, statement, parameters, context 139 | File "/usr/local/lib/python3.7/site-packages/sqlalchemy/engine/default.py", line 588, in do_execute 140 | cursor.execute(statement, parameters) 141 | File "/usr/local/lib/python3.7/site-packages/pymysql/cursors.py", line 170, in execute 142 | result = self._query(query) 143 | File "/usr/local/lib/python3.7/site-packages/pymysql/cursors.py", line 328, in _query 144 | conn.query(q) 145 | File "/usr/local/lib/python3.7/site-packages/pymysql/connections.py", line 516, in query 146 | self._execute_command(COMMAND.COM_QUERY, sql) 147 | File "/usr/local/lib/python3.7/site-packages/pymysql/connections.py", line 771, in _execute_command 148 | self._write_bytes(packet) 149 | File "/usr/local/lib/python3.7/site-packages/pymysql/connections.py", line 718, in _write_bytes 150 | "MySQL server has gone away (%r)" % (e,)) 151 | pymysql.err.OperationalError: (2006, "MySQL server has gone away (ConnectionResetError(104, 'Connection reset by peer'))") 152 | 153 | The above exception was the direct cause of the following exception: 154 | 155 | Traceback (most recent call last): 156 | File "/usr/local/lib/python3.7/site-packages/flask/app.py", line 2446, in wsgi_app 157 | response = self.full_dispatch_request() 158 | File "/usr/local/lib/python3.7/site-packages/flask/app.py", line 1951, in full_dispatch_request 159 | rv = self.handle_user_exception(e) 160 | File "/usr/local/lib/python3.7/site-packages/flask/app.py", line 1820, in handle_user_exception 161 | reraise(exc_type, exc_value, tb) 162 | File "/usr/local/lib/python3.7/site-packages/flask/_compat.py", line 39, in reraise 163 | raise value 164 | File "/usr/local/lib/python3.7/site-packages/flask/app.py", line 1949, in full_dispatch_request 165 | rv = self.dispatch_request() 166 | File "/usr/local/lib/python3.7/site-packages/flask/app.py", line 1935, in dispatch_request 167 | return self.view_functions[rule.endpoint](**req.view_args) 168 | File "/home/NBA_flask/App/views/api.py", line 32, in index 169 | PlayerBasic.teamId == TeamBasic.id).order_by(PlayerBasic.lastNameEn).paginate(page=page,per_page=20) 170 | File "/usr/local/lib/python3.7/site-packages/flask_sqlalchemy/__init__.py", line 496, in paginate 171 | items = self.limit(per_page).offset((page - 1) * per_page).all() 172 | File "/usr/local/lib/python3.7/site-packages/sqlalchemy/orm/query.py", line 3233, in all 173 | return list(self) 174 | File "/usr/local/lib/python3.7/site-packages/sqlalchemy/orm/query.py", line 3389, in __iter__ 175 | return self._execute_and_instances(context) 176 | File "/usr/local/lib/python3.7/site-packages/sqlalchemy/orm/query.py", line 3414, in _execute_and_instances 177 | result = conn.execute(querycontext.statement, self._params) 178 | File "/usr/local/lib/python3.7/site-packages/sqlalchemy/engine/base.py", line 982, in execute 179 | return meth(self, multiparams, params) 180 | File "/usr/local/lib/python3.7/site-packages/sqlalchemy/sql/elements.py", line 293, in _execute_on_connection 181 | return connection._execute_clauseelement(self, multiparams, params) 182 | File "/usr/local/lib/python3.7/site-packages/sqlalchemy/engine/base.py", line 1101, in _execute_clauseelement 183 | distilled_params, 184 | File "/usr/local/lib/python3.7/site-packages/sqlalchemy/engine/base.py", line 1250, in _execute_context 185 | e, statement, parameters, cursor, context 186 | File "/usr/local/lib/python3.7/site-packages/sqlalchemy/engine/base.py", line 1476, in _handle_dbapi_exception 187 | util.raise_from_cause(sqlalchemy_exception, exc_info) 188 | File "/usr/local/lib/python3.7/site-packages/sqlalchemy/util/compat.py", line 398, in raise_from_cause 189 | reraise(type(exception), exception, tb=exc_tb, cause=cause) 190 | File "/usr/local/lib/python3.7/site-packages/sqlalchemy/util/compat.py", line 152, in reraise 191 | raise value.with_traceback(tb) 192 | File "/usr/local/lib/python3.7/site-packages/sqlalchemy/engine/base.py", line 1246, in _execute_context 193 | cursor, statement, parameters, context 194 | File "/usr/local/lib/python3.7/site-packages/sqlalchemy/engine/default.py", line 588, in do_execute 195 | cursor.execute(statement, parameters) 196 | File "/usr/local/lib/python3.7/site-packages/pymysql/cursors.py", line 170, in execute 197 | result = self._query(query) 198 | File "/usr/local/lib/python3.7/site-packages/pymysql/cursors.py", line 328, in _query 199 | conn.query(q) 200 | File "/usr/local/lib/python3.7/site-packages/pymysql/connections.py", line 516, in query 201 | self._execute_command(COMMAND.COM_QUERY, sql) 202 | File "/usr/local/lib/python3.7/site-packages/pymysql/connections.py", line 771, in _execute_command 203 | self._write_bytes(packet) 204 | File "/usr/local/lib/python3.7/site-packages/pymysql/connections.py", line 718, in _write_bytes 205 | "MySQL server has gone away (%r)" % (e,)) 206 | sqlalchemy.exc.OperationalError: (pymysql.err.OperationalError) (2006, "MySQL server has gone away (ConnectionResetError(104, 'Connection reset by peer'))") 207 | [SQL: SELECT player_basic.`playerId` AS `player_basic_playerId`, player_basic.`displayName` AS `player_basic_displayName`, player_basic.`displayNameEn` AS `player_basic_displayNameEn`, team_basic.name AS team_basic_name, player_basic.position AS player_basic_position, player_basic.weight AS player_basic_weight, player_basic.experience AS player_basic_experience, player_basic.country AS player_basic_country 208 | FROM player_basic, team_basic 209 | WHERE player_basic.`teamId` = team_basic.id ORDER BY player_basic.`lastNameEn` 210 | LIMIT %(param_1)s, %(param_2)s] 211 | [parameters: {'param_1': 0, 'param_2': 20}] 212 | (Background on this error at: http://sqlalche.me/e/e3q8) 213 | 194.63.141.147 - - [20/Feb/2020 01:47:36] "GET /player/1 HTTP/1.1" 500 - 214 | 194.63.141.147 - - [20/Feb/2020 01:47:38] "GET /HNAP1/ HTTP/1.1" 404 - 215 | 114.5.130.10 - - [20/Feb/2020 03:09:40] "GET / HTTP/1.1" 302 - 216 | 80.13.134.136 - - [20/Feb/2020 03:39:52] "GET /phpmyadmin/index.php?pma_username=popa3d&pma_password= HTTP/1.1" 404 - 217 | 180.163.220.5 - - [20/Feb/2020 03:56:56] "GET / HTTP/1.1" 302 - 218 | 180.163.220.3 - - [20/Feb/2020 03:56:57] "GET / HTTP/1.1" 302 - 219 | 180.163.220.66 - - [20/Feb/2020 03:56:57] "GET /player/1 HTTP/1.1" 200 - 220 | 180.163.220.5 - - [20/Feb/2020 03:57:58] "GET /detail/1627790 HTTP/1.1" 200 - 221 | 180.163.220.5 - - [20/Feb/2020 03:57:58] "GET /detail/1627790 HTTP/1.1" 200 - 222 | 180.163.220.67 - - [20/Feb/2020 03:58:02] "GET /detail/1627790 HTTP/1.1" 200 - 223 | 180.163.220.3 - - [20/Feb/2020 03:58:03] "GET /detail/1627790 HTTP/1.1" 200 - 224 | 180.163.220.4 - - [20/Feb/2020 04:03:16] "GET /player/1 HTTP/1.1" 200 - 225 | 180.163.220.66 - - [20/Feb/2020 04:03:16] "GET /player/1 HTTP/1.1" 200 - 226 | 180.163.220.3 - - [20/Feb/2020 04:07:49] "GET /player/25 HTTP/1.1" 200 - 227 | 180.163.220.4 - - [20/Feb/2020 04:07:49] "GET /player/25 HTTP/1.1" 200 - 228 | 42.236.10.75 - - [20/Feb/2020 04:07:53] "GET /player/2 HTTP/1.1" 200 - 229 | 42.236.10.114 - - [20/Feb/2020 04:07:53] "GET /player/2 HTTP/1.1" 200 - 230 | 42.236.10.125 - - [20/Feb/2020 04:10:42] "GET /detail/203500 HTTP/1.1" 200 - 231 | 42.236.10.78 - - [20/Feb/2020 04:10:42] "GET /detail/203500 HTTP/1.1" 200 - 232 | 42.236.10.93 - - [20/Feb/2020 04:10:50] "GET /detail/203500 HTTP/1.1" 200 - 233 | 120.78.225.124 - - [20/Feb/2020 04:24:21] "GET / HTTP/1.0" 302 - 234 | 124.13.107.86 - - [20/Feb/2020 06:17:07] "GET / HTTP/1.1" 302 - 235 | 120.24.96.137 - - [20/Feb/2020 06:17:47] "CONNECT 14.215.177.38:80 HTTP/1.1" 404 - 236 | 103.39.10.118 - - [20/Feb/2020 06:17:55] "GET / HTTP/1.1" 302 - 237 | 79.10.247.48 - - [20/Feb/2020 06:22:47] "GET / HTTP/1.1" 302 - 238 | 47.97.23.199 - - [20/Feb/2020 06:48:36] "GET / HTTP/1.0" 302 - 239 | 191.98.246.173 - - [20/Feb/2020 06:49:48] "GET / HTTP/1.1" 302 - 240 | 119.3.220.253 - - [20/Feb/2020 07:17:30] "GET / HTTP/1.1" 302 - 241 | 119.3.220.253 - - [20/Feb/2020 07:17:30] "GET /player/1 HTTP/1.1" 200 - 242 | 85.105.131.247 - - [20/Feb/2020 08:42:56] "GET / HTTP/1.1" 302 - 243 | 66.240.205.34 - - [20/Feb/2020 08:59:09] code 400, message Bad request version ("x64|'|'|No|'|'|0.7d|'|'|..|'|'|AA==|'|'|112.inf|'|'|SGFjS2VkDQoxOTIuMTY4LjkyLjIyMjo1NTUyDQpEZXNrdG9wDQpjbGllbnRhLmV4ZQ0KRmFsc2UNCkZhbHNlDQpUcnVlDQpGYWxzZQ==12.act|'|'|AA==") 244 | 66.240.205.34 - - [20/Feb/2020 08:59:09] "145.ll|'|'|SGFjS2VkX0Q0OTkwNjI3|'|'|WIN-JNAPIER0859|'|'|JNapier|'|'|19-02-01|'|'||'|'|Win 7 Professional SP1 x64|'|'|No|'|'|0.7d|'|'|..|'|'|AA==|'|'|112.inf|'|'|SGFjS2VkDQoxOTIuMTY4LjkyLjIyMjo1NTUyDQpEZXNrdG9wDQpjbGllbnRhLmV4ZQ0KRmFsc2UNCkZhbHNlDQpUcnVlDQpGYWxzZQ==12.act|'|'|AA==" HTTPStatus.BAD_REQUEST - 245 | -------------------------------------------------------------------------------- /L3/feiyan_flask/uwsgi.ini: -------------------------------------------------------------------------------- 1 | 2 | [uwsgi] 3 | 4 | #使用nginx连接时使用，Django程序所在服务器地址 5 | 6 | socket=127.0.0.1:8001 7 | #http=0.0.0.0:80 8 | #module =manage:app 9 | chdir=/home/NBA_flask 10 | wsgi-file=manage.py 11 | callable = app 12 | processes=4 13 | threads=2 14 | master=True 15 | pidfile=uwsgi.pid 16 | daemonize=uwsgi.log 17 | -------------------------------------------------------------------------------- /L3/feiyan_flask/uwsgi.log: -------------------------------------------------------------------------------- 1 | *** Starting uWSGI 2.0.18 (64bit) on [Thu Feb 20 10:02:48 2020] *** 2 | compiled with version: 4.8.5 20150623 (Red Hat 4.8.5-39) on 20 February 2020 01:55:25 3 | os: Linux-3.10.0-1062.9.1.el7.x86_64 #1 SMP Fri Dec 6 15:49:49 UTC 2019 4 | nodename: iZuf66ap4gp7y06vjijgpgZ 5 | machine: x86_64 6 | clock source: unix 7 | pcre jit disabled 8 | detected number of CPU cores: 2 9 | current working directory: /home/NBA_flask 10 | writing pidfile to uwsgi.pid 11 | detected binary path: /usr/local/bin/uwsgi 12 | uWSGI running as root, you can use --uid/--gid/--chroot options 13 | *** WARNING: you are running uWSGI as root !!! (use the --uid flag) *** 14 | chdir() to /home/NBA_flask 15 | your processes number limit is 30631 16 | your memory page size is 4096 bytes 17 | detected max file descriptor number: 65535 18 | lock engine: pthread robust mutexes 19 | thunder lock: disabled (you can enable it with --thunder-lock) 20 | uWSGI http bound on 0.0.0.0:8001 fd 4 21 | uwsgi socket 0 bound to TCP address 127.0.0.1:41714 (port auto-assigned) fd 3 22 | uWSGI running as root, you can use --uid/--gid/--chroot options 23 | *** WARNING: you are running uWSGI as root !!! (use the --uid flag) *** 24 | Python version: 3.7.1 (default, Feb 19 2020, 12:33:04) [GCC 4.8.5 20150623 (Red Hat 4.8.5-39)] 25 | Python main interpreter initialized at 0xc3b930 26 | uWSGI running as root, you can use --uid/--gid/--chroot options 27 | *** WARNING: you are running uWSGI as root !!! (use the --uid flag) *** 28 | python threads support enabled 29 | your server socket listen backlog is limited to 100 connections 30 | your mercy for graceful operations on workers is 60 seconds 31 | mapped 416880 bytes (407 KB) for 8 cores 32 | *** Operational MODE: preforking+threaded *** 33 | unable to find "application" callable in file manage.py 34 | unable to load app 0 (mountpoint='') (callable not found or import error) 35 | *** no app loaded. going in full dynamic mode *** 36 | uWSGI running as root, you can use --uid/--gid/--chroot options 37 | *** WARNING: you are running uWSGI as root !!! (use the --uid flag) *** 38 | *** uWSGI is running in multiple interpreter mode *** 39 | spawned uWSGI master process (pid: 2009) 40 | spawned uWSGI worker 1 (pid: 2010, cores: 2) 41 | spawned uWSGI worker 2 (pid: 2012, cores: 2) 42 | spawned uWSGI worker 3 (pid: 2013, cores: 2) 43 | spawned uWSGI worker 4 (pid: 2015, cores: 2) 44 | spawned uWSGI http 1 (pid: 2016) 45 | SIGINT/SIGQUIT received...killing workers... 46 | gateway "uWSGI http 1" has been buried (pid: 2016) 47 | worker 1 buried after 1 seconds 48 | worker 2 buried after 1 seconds 49 | worker 3 buried after 1 seconds 50 | worker 4 buried after 1 seconds 51 | goodbye to uWSGI. 52 | *** Starting uWSGI 2.0.18 (64bit) on [Thu Feb 20 10:06:08 2020] *** 53 | compiled with version: 4.8.5 20150623 (Red Hat 4.8.5-39) on 20 February 2020 01:55:25 54 | os: Linux-3.10.0-1062.9.1.el7.x86_64 #1 SMP Fri Dec 6 15:49:49 UTC 2019 55 | nodename: iZuf66ap4gp7y06vjijgpgZ 56 | machine: x86_64 57 | clock source: unix 58 | pcre jit disabled 59 | detected number of CPU cores: 2 60 | current working directory: /home/NBA_flask 61 | writing pidfile to uwsgi.pid 62 | detected binary path: /usr/local/bin/uwsgi 63 | uWSGI running as root, you can use --uid/--gid/--chroot options 64 | *** WARNING: you are running uWSGI as root !!! (use the --uid flag) *** 65 | chdir() to /home/NBA_flask 66 | your processes number limit is 30631 67 | your memory page size is 4096 bytes 68 | detected max file descriptor number: 65535 69 | lock engine: pthread robust mutexes 70 | thunder lock: disabled (you can enable it with --thunder-lock) 71 | uWSGI http bound on 0.0.0.0:80 fd 4 72 | uwsgi socket 0 bound to TCP address 127.0.0.1:33579 (port auto-assigned) fd 3 73 | uWSGI running as root, you can use --uid/--gid/--chroot options 74 | *** WARNING: you are running uWSGI as root !!! (use the --uid flag) *** 75 | Python version: 3.7.1 (default, Feb 19 2020, 12:33:04) [GCC 4.8.5 20150623 (Red Hat 4.8.5-39)] 76 | Python main interpreter initialized at 0xe7e930 77 | uWSGI running as root, you can use --uid/--gid/--chroot options 78 | *** WARNING: you are running uWSGI as root !!! (use the --uid flag) *** 79 | python threads support enabled 80 | your server socket listen backlog is limited to 100 connections 81 | your mercy for graceful operations on workers is 60 seconds 82 | mapped 416880 bytes (407 KB) for 8 cores 83 | *** Operational MODE: preforking+threaded *** 84 | unable to find "application" callable in file manage.py 85 | unable to load app 0 (mountpoint='') (callable not found or import error) 86 | *** no app loaded. going in full dynamic mode *** 87 | uWSGI running as root, you can use --uid/--gid/--chroot options 88 | *** WARNING: you are running uWSGI as root !!! (use the --uid flag) *** 89 | *** uWSGI is running in multiple interpreter mode *** 90 | spawned uWSGI master process (pid: 2186) 91 | spawned uWSGI worker 1 (pid: 2187, cores: 2) 92 | spawned uWSGI worker 2 (pid: 2188, cores: 2) 93 | spawned uWSGI worker 3 (pid: 2190, cores: 2) 94 | spawned uWSGI worker 4 (pid: 2192, cores: 2) 95 | spawned uWSGI http 1 (pid: 2193) 96 | --- no python application found, check your startup logs for errors --- 97 | [pid: 2190|app: -1|req: -1/1] 183.192.95.88 () {38 vars in 720 bytes} [Thu Feb 20 10:06:14 2020] GET /player/1 => generated 21 bytes in 0 msecs (HTTP/1.1 500) 2 headers in 83 bytes (0 switches on core 0) 98 | --- no python application found, check your startup logs for errors --- 99 | [pid: 2190|app: -1|req: -1/2] 183.192.95.88 () {36 vars in 673 bytes} [Thu Feb 20 10:06:22 2020] GET / => generated 21 bytes in 0 msecs (HTTP/1.1 500) 2 headers in 83 bytes (0 switches on core 1) 100 | SIGINT/SIGQUIT received...killing workers... 101 | gateway "uWSGI http 1" has been buried (pid: 2193) 102 | worker 1 buried after 1 seconds 103 | worker 2 buried after 1 seconds 104 | worker 3 buried after 1 seconds 105 | worker 4 buried after 1 seconds 106 | goodbye to uWSGI. 107 | *** Starting uWSGI 2.0.18 (64bit) on [Thu Feb 20 10:12:25 2020] *** 108 | compiled with version: 4.8.5 20150623 (Red Hat 4.8.5-39) on 20 February 2020 01:55:25 109 | os: Linux-3.10.0-1062.9.1.el7.x86_64 #1 SMP Fri Dec 6 15:49:49 UTC 2019 110 | nodename: iZuf66ap4gp7y06vjijgpgZ 111 | machine: x86_64 112 | clock source: unix 113 | pcre jit disabled 114 | detected number of CPU cores: 2 115 | current working directory: /home/NBA_flask 116 | writing pidfile to uwsgi.pid 117 | detected binary path: /usr/local/bin/uwsgi 118 | uWSGI running as root, you can use --uid/--gid/--chroot options 119 | *** WARNING: you are running uWSGI as root !!! (use the --uid flag) *** 120 | chdir() to /home/NBA_flask 121 | your processes number limit is 30631 122 | your memory page size is 4096 bytes 123 | detected max file descriptor number: 65535 124 | lock engine: pthread robust mutexes 125 | thunder lock: disabled (you can enable it with --thunder-lock) 126 | uWSGI http bound on 0.0.0.0:80 fd 4 127 | uwsgi socket 0 bound to TCP address 127.0.0.1:35020 (port auto-assigned) fd 3 128 | uWSGI running as root, you can use --uid/--gid/--chroot options 129 | *** WARNING: you are running uWSGI as root !!! (use the --uid flag) *** 130 | Python version: 3.7.1 (default, Feb 19 2020, 12:33:04) [GCC 4.8.5 20150623 (Red Hat 4.8.5-39)] 131 | Python main interpreter initialized at 0x12d3920 132 | uWSGI running as root, you can use --uid/--gid/--chroot options 133 | *** WARNING: you are running uWSGI as root !!! (use the --uid flag) *** 134 | python threads support enabled 135 | your server socket listen backlog is limited to 100 connections 136 | your mercy for graceful operations on workers is 60 seconds 137 | mapped 416880 bytes (407 KB) for 8 cores 138 | *** Operational MODE: preforking+threaded *** 139 | WSGI app 0 (mountpoint='') ready in 1 seconds on interpreter 0x12d3920 pid: 2513 (default app) 140 | uWSGI running as root, you can use --uid/--gid/--chroot options 141 | *** WARNING: you are running uWSGI as root !!! (use the --uid flag) *** 142 | *** uWSGI is running in multiple interpreter mode *** 143 | spawned uWSGI master process (pid: 2513) 144 | spawned uWSGI worker 1 (pid: 2514, cores: 2) 145 | spawned uWSGI worker 2 (pid: 2516, cores: 2) 146 | spawned uWSGI worker 3 (pid: 2517, cores: 2) 147 | spawned uWSGI worker 4 (pid: 2519, cores: 2) 148 | spawned uWSGI http 1 (pid: 2520) 149 | /usr/local/lib/python3.7/site-packages/pymysql/cursors.py:170: Warning: (3719, "'utf8' is currently an alias for the character set UTF8MB3, but will be an alias for UTF8MB4 in a future release. Please consider using UTF8MB4 in order to be unambiguous.") 150 | result = self._query(query) 151 | 152 | [pid: 2517|app: 0|req: 1/1] 183.192.95.88 () {38 vars in 719 bytes} [Thu Feb 20 10:12:32 2020] GET /player/1 => generated 10126 bytes in 105 msecs (HTTP/1.1 200) 2 headers in 82 bytes (1 switches on core 0) 153 | 154 | [pid: 2517|app: 0|req: 2/2] 183.192.95.88 () {38 vars in 719 bytes} [Thu Feb 20 10:12:41 2020] GET /player/1 => generated 10126 bytes in 18 msecs (HTTP/1.1 200) 2 headers in 82 bytes (1 switches on core 1) 155 | SIGINT/SIGQUIT received...killing workers... 156 | gateway "uWSGI http 1" has been buried (pid: 2520) 157 | worker 1 buried after 1 seconds 158 | worker 2 buried after 1 seconds 159 | worker 3 buried after 1 seconds 160 | worker 4 buried after 1 seconds 161 | goodbye to uWSGI. 162 | *** Starting uWSGI 2.0.18 (64bit) on [Thu Feb 20 10:23:05 2020] *** 163 | compiled with version: 4.8.5 20150623 (Red Hat 4.8.5-39) on 20 February 2020 01:55:25 164 | os: Linux-3.10.0-1062.9.1.el7.x86_64 #1 SMP Fri Dec 6 15:49:49 UTC 2019 165 | nodename: iZuf66ap4gp7y06vjijgpgZ 166 | machine: x86_64 167 | clock source: unix 168 | pcre jit disabled 169 | detected number of CPU cores: 2 170 | current working directory: /home/NBA_flask 171 | writing pidfile to uwsgi.pid 172 | detected binary path: /usr/local/bin/uwsgi 173 | uWSGI running as root, you can use --uid/--gid/--chroot options 174 | *** WARNING: you are running uWSGI as root !!! (use the --uid flag) *** 175 | chdir() to /home/NBA_flask 176 | your processes number limit is 30631 177 | your memory page size is 4096 bytes 178 | detected max file descriptor number: 65535 179 | lock engine: pthread robust mutexes 180 | thunder lock: disabled (you can enable it with --thunder-lock) 181 | uwsgi socket 0 bound to TCP address 127.0.0.1:8001 fd 3 182 | uWSGI running as root, you can use --uid/--gid/--chroot options 183 | *** WARNING: you are running uWSGI as root !!! (use the --uid flag) *** 184 | Python version: 3.7.1 (default, Feb 19 2020, 12:33:04) [GCC 4.8.5 20150623 (Red Hat 4.8.5-39)] 185 | Python main interpreter initialized at 0x2890820 186 | uWSGI running as root, you can use --uid/--gid/--chroot options 187 | *** WARNING: you are running uWSGI as root !!! (use the --uid flag) *** 188 | python threads support enabled 189 | your server socket listen backlog is limited to 100 connections 190 | your mercy for graceful operations on workers is 60 seconds 191 | mapped 416880 bytes (407 KB) for 8 cores 192 | *** Operational MODE: preforking+threaded *** 193 | WSGI app 0 (mountpoint='') ready in 0 seconds on interpreter 0x2890820 pid: 3132 (default app) 194 | uWSGI running as root, you can use --uid/--gid/--chroot options 195 | *** WARNING: you are running uWSGI as root !!! (use the --uid flag) *** 196 | *** uWSGI is running in multiple interpreter mode *** 197 | spawned uWSGI master process (pid: 3132) 198 | spawned uWSGI worker 1 (pid: 3133, cores: 2) 199 | spawned uWSGI worker 2 (pid: 3135, cores: 2) 200 | spawned uWSGI worker 3 (pid: 3136, cores: 2) 201 | spawned uWSGI worker 4 (pid: 3138, cores: 2) 202 | [pid: 3135|app: 0|req: 1/1] 183.192.95.88 () {46 vars in 831 bytes} [Thu Feb 20 10:23:26 2020] GET / => generated 225 bytes in 15 msecs (HTTP/1.1 302) 3 headers in 124 bytes (1 switches on core 0) 203 | /usr/local/lib/python3.7/site-packages/pymysql/cursors.py:170: Warning: (3719, "'utf8' is currently an alias for the character set UTF8MB3, but will be an alias for UTF8MB4 in a future release. Please consider using UTF8MB4 in order to be unambiguous.") 204 | result = self._query(query) 205 | 206 | [pid: 3138|app: 0|req: 1/2] 183.192.95.88 () {42 vars in 755 bytes} [Thu Feb 20 10:23:26 2020] GET /player/1 => generated 10126 bytes in 113 msecs (HTTP/1.1 200) 2 headers in 82 bytes (1 switches on core 0) 207 | [pid: 3138|app: 0|req: 2/3] 183.192.95.88 () {42 vars in 779 bytes} [Thu Feb 20 10:33:19 2020] GET /detail/203500 => generated 992 bytes in 16 msecs (HTTP/1.1 200) 2 headers in 80 bytes (1 switches on core 1) 208 | [pid: 3138|app: 0|req: 3/4] 183.192.95.88 () {42 vars in 779 bytes} [Thu Feb 20 10:33:28 2020] GET /detail/203937 => generated 992 bytes in 11 msecs (HTTP/1.1 200) 2 headers in 80 bytes (1 switches on core 0) 209 | [pid: 3138|app: 0|req: 4/5] 186.251.231.22 () {32 vars in 452 bytes} [Thu Feb 20 10:43:11 2020] GET / => generated 225 bytes in 1 msecs (HTTP/1.1 302) 3 headers in 124 bytes (1 switches on core 1) 210 | [pid: 3138|app: 0|req: 5/6] 80.82.70.187 () {32 vars in 420 bytes} [Thu Feb 20 10:46:04 2020] GET /cache/global/img/gs.gif => generated 232 bytes in 1 msecs (HTTP/1.1 404) 2 headers in 87 bytes (1 switches on core 0) 211 | -------------------------------------------------------------------------------- /L3/feiyan_flask/uwsgi.pid: -------------------------------------------------------------------------------- 1 | 3132 2 | -------------------------------------------------------------------------------- /L3/find_median.py: -------------------------------------------------------------------------------- 1 | """ 2 | 寻找两个有序数组的中位数 3 | 利用二分查找的优势，求解 4 | """ 5 | 6 | # 在nums1[start1,end1], nums2[start2, end2]两个数组中，找第k小的数 7 | def get_kth_num(nums1, start1, end1, nums2, start2, end2, k): 8 | len1 = end1 - start1 + 1 9 | len2 = end2 - start2 + 1 10 | 11 | # 让 len1 的长度小于 len2，这样就能保证如果有数组空了，一定是 len1 12 | if len1 > len2: 13 | return get_kth_num(nums2, start2, end2, nums1, start1, end1, k) 14 | if len1 == 0: 15 | return nums2[start2 + k - 1] 16 | 17 | if k == 1: 18 | return min(nums1[start1], nums2[start2]) 19 | 20 | # 两个数组，分别前进k/2个数 21 | i = int(start1 + min(len1, k / 2) - 1) 22 | j = int(start2 + min(len2, k / 2) - 1) 23 | 24 | if nums1[i] < nums2[j]: 25 | # 第一个数组，前k/2去掉，在剩余的数组中，继续查找 26 | return get_kth_num(nums1, i + 1, end1, nums2, start2, end2, k - (i - start1 + 1)) 27 | else: 28 | # 第二个数组，前k/2去掉，在剩余的数组中，继续查找 29 | return get_kth_num(nums1, start1, end1, nums2, j + 1, end2, k - (j - start2 + 1)) 30 | 31 | # 找两个有序数组中的中位数 32 | def find_median(nums1, nums2): 33 | n = len(nums1) 34 | m = len(nums2) 35 | # 第一个中位数 36 | left = int((n + m + 1) / 2) 37 | # 第二个中位数 38 | right = int((n + m + 2) / 2) 39 | 40 | if left == right: 41 | result = get_kth_num(nums1, 0, n - 1, nums2, 0, m - 1, left) 42 | else: 43 | result = (get_kth_num(nums1, 0, n - 1, nums2, 0, m - 1, left) + get_kth_num(nums1, 0, n - 1, nums2, 0, m - 1, right)) / 2 44 | return result 45 | 46 | """ 47 | nums1 = [1, 2, 3] 48 | nums2 = [4, 5] 49 | """ 50 | nums1 = [1, 3, 5, 7] 51 | nums2 = [1,2,3,4,5,6,7,8,9,10] 52 | 53 | print (find_median(nums1, nums2)) 54 | 55 | -------------------------------------------------------------------------------- /L3/homework/Action1.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cystanford/Data_Analysis_with_Python/a33b965d98612031a0effe17a9c6da3a1eaefb5e/L3/homework/Action1.md -------------------------------------------------------------------------------- /L3/homework/word_cloud1.py: -------------------------------------------------------------------------------- 1 | # -*- coding:utf-8 -*- 2 | # 生成词云 3 | from wordcloud import WordCloud 4 | import pandas as pd 5 | import matplotlib.pyplot as plt 6 | from PIL import Image 7 | import numpy as np 8 | from lxml import etree 9 | from nltk.tokenize import word_tokenize 10 | 11 | # 去掉停用词 12 | def remove_stop_words(f): 13 | stop_words = ['nan'] 14 | for stop_word in stop_words: 15 | f = f.replace(stop_word, '') 16 | return f 17 | 18 | # 生成词云 19 | def create_word_cloud(f): 20 | print('根据词频，开始生成词云!') 21 | f = remove_stop_words(f) 22 | cut_text = word_tokenize(f) 23 | #print(cut_text) 24 | cut_text = " ".join(cut_text) 25 | wc = WordCloud( 26 | max_words=100, 27 | width=2000, 28 | height=1200, 29 | ) 30 | wordcloud = wc.generate(cut_text) 31 | # 写词云图片 32 | wordcloud.to_file("wordcloud.jpg") 33 | # 显示词云文件 34 | plt.imshow(wordcloud) 35 | plt.axis("off") 36 | plt.show() 37 | 38 | # 数据加载 39 | data = pd.read_csv('./Market_Basket_Optimisation.csv', header = None) 40 | transactions = [] 41 | for i in range(0, data.shape[0]): 42 | transactions.append([str(data.values[i, j]) for j in range(0, 20)]) 43 | 44 | all_word = " ".join('%s' %id for id in transactions) 45 | #print(all_word) 46 | # 生成词云 47 | create_word_cloud(all_word) 48 | -------------------------------------------------------------------------------- /L3/homework/wordcloud.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cystanford/Data_Analysis_with_Python/a33b965d98612031a0effe17a9c6da3a1eaefb5e/L3/homework/wordcloud.jpg -------------------------------------------------------------------------------- /L3/wordcloud/movies_word_cloud.py: -------------------------------------------------------------------------------- 1 | # -*- coding:utf-8 -*- 2 | # 词云展示 3 | from wordcloud import WordCloud 4 | import pandas as pd 5 | import matplotlib.pyplot as plt 6 | from PIL import Image 7 | import numpy as np 8 | from lxml import etree 9 | from nltk.tokenize import word_tokenize 10 | 11 | # 去掉停用词 12 | def remove_stop_words(f): 13 | stop_words = ['Movie'] 14 | for stop_word in stop_words: 15 | f = f.replace(stop_word, '') 16 | return f 17 | 18 | # 生成词云 19 | def create_word_cloud(f): 20 | print('根据词频，开始生成词云!') 21 | f = remove_stop_words(f) 22 | cut_text = word_tokenize(f) 23 | #print(cut_text) 24 | cut_text = " ".join(cut_text) 25 | wc = WordCloud( 26 | max_words=100, 27 | width=2000, 28 | height=1200, 29 | ) 30 | wordcloud = wc.generate(cut_text) 31 | # 写词云图片 32 | wordcloud.to_file("wordcloud.jpg") 33 | # 显示词云文件 34 | plt.imshow(wordcloud) 35 | plt.axis("off") 36 | plt.show() 37 | 38 | # 数据加载 39 | data = pd.read_csv('./movies.csv') 40 | # 读取title 和 genres字段 41 | title = " ".join(data['title']) 42 | genres = " ".join(data['genres']) 43 | all_word = title + genres 44 | # 生成词云 45 | create_word_cloud(all_word) 46 | -------------------------------------------------------------------------------- /L4/anjuke/anjuke_bs.py: -------------------------------------------------------------------------------- 1 | # 使用request + BeautifulSoup提取安居客北京二手房信息 2 | import requests 3 | from bs4 import BeautifulSoup 4 | 5 | # 请求URL 6 | url = 'https://beijing.anjuke.com/sale/p1' 7 | 8 | # 得到页面的内容 9 | headers={'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36'} 10 | html=requests.get(url,headers=headers,timeout=10) 11 | content = html.text 12 | #print(content) 13 | 14 | # 通过content创建BeautifulSoup对象 15 | soup = BeautifulSoup(content, 'html.parser', from_encoding='utf-8') 16 | #输出第一个 title 标签 17 | print(soup.title) 18 | #输出第一个 title 标签的标签名称 19 | print(soup.title.name) 20 | #输出第一个 title 标签的包含内容 21 | print(soup.title.string) 22 | 23 | 24 | # 找到class="list-item"下面的所有li标签 25 | house_list=soup.find_all('li',class_="list-item") 26 | # 提取房源信息 27 | for house in house_list: 28 | # 提取房源信息 29 | name = house.find('div',class_="house-title").a.text.strip() 30 | details = house.find('div',class_='details-item').text.strip() 31 | address = house.find('span',class_="comm-address").text.strip() 32 | print('address', address) 33 | tags = house.find('div',class_='tags-bottom').text.strip() 34 | print('tags', tags) 35 | broker = house.find('div',class_="broker-item").text.strip() 36 | print('broker', broker) 37 | price = house.find('span',class_="price-det").text.strip() 38 | print('price', price) 39 | unit_price = house.find('span',class_="unit-price").text.strip() 40 | print('unit_price', unit_price) 41 | print(name, details, address, tags, broker, price, unit_price) 42 | -------------------------------------------------------------------------------- /L4/anjuke/anjuke_selenium.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | # 使用Selenium, 北京安居客->小区->二手房信息 3 | import json 4 | import requests 5 | from lxml import etree 6 | import time 7 | from selenium import webdriver 8 | import pandas as pd 9 | 10 | # 需要将chromedriver放到Chrome\Application目录下 11 | driver = webdriver.Chrome() 12 | 13 | # 去空格，去换行\n 14 | def format_str(str): 15 | return str.replace('\n', '').replace(' ', '') 16 | 17 | # 对页面进行抓取分析 18 | def work(request_url): 19 | driver.get(request_url) 20 | time.sleep(1) 21 | html = driver.find_element_by_xpath("//*").get_attribute("outerHTML") 22 | html = etree.HTML(html) 23 | # 设置需要抓取字段的xpath 24 | titles = html.xpath("/html/body/div[@class='w1180']/div[@class='maincontent']/div[@id='list-content']/div[@class='li-itemmod']/div[@class='li-info']//a/@title") 25 | links = html.xpath("/html/body/div[@class='w1180']/div[@class='maincontent']/div[@id='list-content']/div[@class='li-itemmod']/div[@class='li-info']//a/@href") 26 | addresses = html.xpath("/html/body/div[@class='w1180']/div[@class='maincontent']/div[@id='list-content']/div[@class='li-itemmod']/div[@class='li-info']/address/text()") 27 | prices = html.xpath("/html/body/div[@class='w1180']/div[@class='maincontent']/div[@id='list-content']/div[@class='li-itemmod']/div[@class='li-side']/p[1]/strong/text()") 28 | to_last_months = html.xpath("/html/body/div[@class='w1180']/div[@class='maincontent']/div[@id='list-content']/div[@class='li-itemmod']/div[@class='li-side']/p[2]/text()") 29 | completion_dates = html.xpath("/html/body/div[@class='w1180']/div[@class='maincontent']/div[@id='list-content']/div[@class='li-itemmod']/div[@class='li-info']/p[1]/text()[1]") 30 | houses = pd.DataFrame(columns = ['title', 'link', 'address', 'price', 'to_last_month', 'completion_date']) 31 | for i in range(len(titles)): 32 | # 设置抓取的房源 33 | temp = {} 34 | temp['title'] = format_str(titles[i]) 35 | temp['link'] = format_str(links[i]) 36 | temp['address'] = format_str(addresses[i]) 37 | temp['price'] = format_str(prices[i]) 38 | temp['to_last_month'] = format_str(to_last_months[i]) 39 | temp['completion_date'] = format_str(completion_dates[i]) 40 | # 添加房源 41 | houses = houses.append(temp,ignore_index=True) 42 | return houses 43 | 44 | # 抓取10页北京房价数据 45 | page_num = 10 46 | base_url = 'https://beijing.anjuke.com/community/p' 47 | houses = pd.DataFrame(columns = ['title', 'link', 'address', 'price', 'to_last_month', 'completion_date']) 48 | for i in range(page_num): 49 | request_url = base_url+str(i+1) 50 | print(request_url) 51 | # 抓取该页的房源信息 52 | temp = work(request_url) 53 | houses = houses.append(temp) 54 | print(temp) 55 | houses.to_csv('house_prices_bj.csv') 56 | 57 | 58 | -------------------------------------------------------------------------------- /L4/anjuke/auto_login.py: -------------------------------------------------------------------------------- 1 | # 自动登录开课吧学习中心 提交表单 2 | import time 3 | from selenium import webdriver 4 | 5 | # 需要将chromedriver放到Chrome\Application目录下 6 | driver = webdriver.Chrome() 7 | 8 | request_url = 'http://student.kaikeba.com/user/login' 9 | driver.get(request_url) 10 | 11 | driver.find_element_by_id('username').send_keys('13520355196') 12 | driver.find_element_by_id('password').send_keys('helloworld') 13 | driver.find_element_by_class_name('submit').click() 14 | -------------------------------------------------------------------------------- /L4/anjuke/bs_demo.py: -------------------------------------------------------------------------------- 1 | # 使用BeautifulSoup分析HTML页面内容 2 | from bs4 import BeautifulSoup 3 | 4 | #待分析字符串 5 | html_doc = """ 6 | 7 | 8 | BeautifulSoup Demo 9 | 10 | 11 |

12 | 13 | Here is the content 14 | 15 |

16 |

Python爬虫有很多优秀的工具 17 | BeautifulSoup, 18 | Selenium 19 | and 20 | Scrapy 21 | 他们都可以帮你爬虫想要的页面内容 22 |

23 |

...

24 | """ 25 | 26 | # 通过html字符串创建BeautifulSoup对象 27 | soup = BeautifulSoup(html_doc, 'html.parser', from_encoding='utf-8') 28 | 29 | #输出第一个 title 标签 30 | print(soup.title) 31 | #输出第一个 title 标签的标签名称 32 | print(soup.title.name) 33 | #输出第一个 title 标签的包含内容 34 | print(soup.title.string) 35 | #输出第一个 title 标签的父标签的标签名称 36 | print(soup.title.parent.name) 37 | 38 | 39 | #输出第一个p标签 40 | print(soup.p) 41 | #输出第一个 p 标签的 class 属性内容 42 | print(soup.p['class']) 43 | 44 | #输出第一个 a 标签的 href 属性内容 45 | print(soup.a['href']) 46 | # soup的属性操作方法与字典一样，可以被添加,删除或修改. 47 | # 修改第一个 a 标签的href属性为 http://www.baidu.com/ 48 | soup.a['href'] = 'http://www.baidu.com/' 49 | #给第一个 a 标签添加 name 属性 50 | soup.a['name'] = u'百度' 51 | print(soup.a) 52 | #删除第一个 a 标签的 class 属性为 53 | del soup.a['class'] 54 | print(soup.a) 55 | -------------------------------------------------------------------------------- /L4/pagerank/Aliases.csv: -------------------------------------------------------------------------------- 1 | Id,Alias,PersonId 2 | 1,111th congress,1 3 | 2,agna usemb kabul afghanistan,2 4 | 3,ap,3 5 | 4,asuncion,4 6 | 5,alec,5 7 | 6,dupuy alex,6 8 | 7,american beverage association,7 9 | 8,mayock andrew,8 10 | 9,shapiro andrew j,9 11 | 10,shapiroa@state.gov,9 12 | 11,slaughter annmarie,10 13 | 12,slaughter anne marie,10 14 | 13,slaughter annemarie,10 15 | 14,slaughtera@state.gov,10 16 | 15,lake anthony,11 17 | 16,valenzuela arturo a,12 18 | 17,valenzuelaaa@state.gov,12 19 | 18,kimoon ban,13 20 | 19,obama barack,14 21 | 20,president,14 22 | 21,bam@mikulski.senate.gov,15 23 | 22,mikulski bam,15 24 | 23,mikulski bam (mikulski),15 25 | 24,mikulski bam (mitkulski),15 26 | 25,mikulskibam (mikulski),15 27 | 26,betsy.ebeling,16 28 | 27,ebeling betsy,16 29 | 28,betsyebeling,16 30 | 29,betsyebeling1050,16 31 | 30,clinton william j,17 32 | 31,dad,17 33 | 32,biography,18 34 | 33,klehr bonnie,19 35 | 34,brian,20 36 | 35,bstrider,21 37 | 36,strider burns,21 38 | 37,capricia marshall,22 39 | 38,marshall capricia,22 40 | 39,marshall capricia p,22 41 | 40,capriciamarshall,22 42 | 41,capriciamarshall@,22 43 | 42,cmarshall,22 44 | 43,marshallcp@state.gov,22 45 | 44,pascual carlos,23 46 | 45,adler caroline e,24 47 | 46,button case,25 48 | 47,richards cecile,26 49 | 48,eur/rus:weson chad,27 50 | 49,nea/pi/ce:kiamie charles,28 51 | 50,chelsea,29 52 | 51,blair cherie,30 53 | 52,cherie blair,30 54 | 53,cb,30 55 | 54,cherieblair,30 56 | 55,cheryl,31 57 | 56,c:mills cheryl,32 58 | 57,cheryl mills,32 59 | 58,cheryl mills cos,32 60 | 59,mill cheryl,32 61 | 60,mills cherlyl d,32 62 | 61,mills chery d,32 63 | 62,mills cheryl,32 64 | 63,mills cheryl d,32 65 | 64,millscheryl d,32 66 | 65,mills. cherl d,32 67 | 66,mills. cheryl d,32 68 | 67,millscd@state.gov,32 69 | 68,cheryl.mills,32 70 | 69,cheryl.mills@,32 71 | 70,crocker chester a,33 72 | 71,butzgy christopher h,34 73 | 72,edwards christopher,35 74 | 73,eap/j:green christopher,36 75 | 74,hill christopher r (baghdad),37 76 | 75,hillcr@state.gov,37 77 | 76,coleman claire l,38 78 | 77,colin powell,39 79 | 78,council on foreign relations,40 80 | 79,beale courtney a karamer,41 81 | 80,beale courtney a kramer,41 82 | 81,bealeca@state.gov,41 83 | 82,kelly craig a,42 84 | 83,daily sun,43 85 | 84,hyde dana,44 86 | 85,daniel,45 87 | 86,baer daniel,46 88 | 87,baer daniel b,46 89 | 88,baer daniel d,46 90 | 89,baer.daniel,46 91 | 90,daniel.baer,46 92 | 91,inonye daniel,47 93 | 92,schwerin daniel b,48 94 | 93,schwerindb@state.gov,48 95 | 94,brian danielle,49 96 | 95,axelrod david m,50 97 | 96,axelrod_d,50 98 | 97,brock david,51 99 | 98,david_garten@lautenberg.senate.gov,52 100 | 99,garten david (lautenberg),52 101 | 100,inl:johnson david t,53 102 | 101,d.gunners2010,54 103 | 102,department of state,55 104 | 103,chollet derek h,56 105 | 104,cholletdh@state.gov,56 106 | 105,reynolds diane,57 107 | 106,donald,58 108 | 107,band doug,59 109 | 108,hattaway doug,60 110 | 109,doug,60 111 | 110,pelton e,61 112 | 111,politico drew elizabeth,62 113 | 112,tauscher ellen o,63 114 | 113,tauschereo@state.gov,63 115 | 114,faleomavaega eni f,64 116 | 115,woodard eric w,65 117 | 116,brimmer esther d,66 118 | 117,brimmere@state.gov,66 119 | 118,finca international,67 120 | 119,foreign affairs magazine,68 121 | 120,prm/mce:wills g,69 122 | 121,lou de bac g/tip,70 123 | 122,prm/mce:willsg,71 124 | 123,mitchell george,72 125 | 124,glantz gina,73 126 | 125,glantz.,73 127 | 126,govenman etazini,74 128 | 127,haiti,75 129 | 128,duksoo han,76 130 | 129,koh harold hongju,77 131 | 130,kohhh@state.gov,77 132 | 131,heintz,78 133 | 132,hill,79 134 | 133,hillary clinton,80 135 | 134,clinton,80 136 | 135,clinton hillary r,80 137 | 136,clinton hillary,80 138 | 137,clinton hillary rodham,80 139 | 138,h,80 140 | 139,h2,80 141 | 140,hrc,80 142 | 141,hillary,80 143 | 142,hillary rodham clinton,80 144 | 143,madam secretary,80 145 | 144,secretary,80 146 | 145,secretary clinton,80 147 | 146,secretary of state,80 148 | 147,hr15@mycingular.blackberry.net,80 149 | 148,hrod17@clintonemail.com,80 150 | 149,the honorable hillary rodham clinton secretary of state,80 151 | 150,hdr22@clintonemail.com,80 152 | 151,abedin huma,81 153 | 152,abedinh@state.gov,81 154 | 153,abein huma,81 155 | 154,abendin huma,81 156 | 155,adedin huma,81 157 | 156,huma abedin,81 158 | 157,huma@clintonemail.com,81 159 | 158,abedin@state.gov,81 160 | 159,abendinh@state.gov,81 161 | 160,adedinh@state.gov,81 162 | 161,kelly ian,82 163 | 162,ds/pa:finkle j,83 164 | 163,jama,84 165 | 164,newmyer jackie,85 166 | 165,newmyer,85 167 | 166,lew,86 168 | 167,lew jacob,86 169 | 168,lew jacob j,86 170 | 169,jacobjlew,86 171 | 170,lewjj@state.gov,86 172 | 171,sullivan jj@state.gov,87 173 | 172,sullivan jacbo j,87 174 | 173,sullivan jack,87 175 | 174,sullivan jacob,87 176 | 175,sullivan jacob h,87 177 | 176,sullivan jacob j,87 178 | 177,sullivan jake,87 179 | 178,sullivan jake j,87 180 | 179,sullivanjj@state.gov,87 181 | 180,jake. sullivan,87 182 | 181,jake.sullivan,87 183 | 182,jake.sullivan@,87 184 | 183,sulllivanjj@state.gov,87 185 | 184,sullivanil@state.gov,87 186 | 185,sullivann@state.gov.,87 187 | 186,mcgovern james p,88 188 | 187,smith james e,89 189 | 188,steinberg james b,90 190 | 189,steinbergjb@state.gov,90 191 | 190,steinbertjb@state.gov,90 192 | 191,jpiercy,91 193 | 192,jacobs janice l,92 194 | 193,farrow jeffrey,93 195 | 194,farrow jeffrey l,93 196 | 195,jfarrow,93 197 | 196,feltman jeffrey d,94 198 | 197,feltmanjd@state.gov,94 199 | 198,robinson jennifer,95 200 | 199,hoagland jim,96 201 | 200,kennedy jim,97 202 | 201,laszczych joanne,98 203 | 202,olver john,99 204 | 203,podesta john,100 205 | 204,jpodesta,100 206 | 205,carson johnnie,101 207 | 206,carsonj@state.gov,101 208 | 207,jonathan prince,102 209 | 208,daniel joshua j,103 210 | 209,kieffer judith,104 211 | 210,mchale judith,105 212 | 211,mchale judith a,105 213 | 212,mchaleja@state.gov,105 214 | 213,cooper justin,106 215 | 214,kpk,107 216 | 215,kabul lgf request,108 217 | 216,eikenberry karl w,109 218 | 217,kellyc@state.gov,110 219 | 218,conrad kent,111 220 | 219,baldersonkm@state.gov,112 221 | 220,balderston kris m,112 222 | 221,balderstone kris m,112 223 | 222,balderstonkm@state.gov,112 224 | 223,campbell kurt m,113 225 | 224,campbellkm@state.gov,113 226 | 225,eap/k:rosenberger l,114 227 | 226,lgraham,115 228 | 227,jilloty lauren c,116 229 | 228,jiloty cheryl d,116 230 | 229,jiloty lauren,116 231 | 230,jiloty lauren c,116 232 | 231,jiloty lauren cd,116 233 | 232,jiloty. lauren c,116 234 | 233,jilotylc@state.gov,116 235 | 234,jjiloty lauren c,116 236 | 235,jjilotylc@state.gov,116 237 | 236,lauren jiloty,116 238 | 237,rubiner laurie,117 239 | 238,brown lee r,118 240 | 239,feinstein lee,119 241 | 240,dewan linda l,120 242 | 241,captuol,121 243 | 242,caputol,121 244 | 243,imuscatine,122 245 | 244,lissa muscatine,122 246 | 245,muscantine lissa,122 247 | 246,muscatine lissa,122 248 | 247,muscatine lisa,122 249 | 248,muscatinelissa,122 250 | 249,muscatine. lissa,122 251 | 250,muscatinel@state.gov,122 252 | 251,lmuscatine,122 253 | 252,muscantinel@state.gov,122 254 | 253,quam lois,123 255 | 254,valmmorolj@state.gov,124 256 | 255,valmoro lona,124 257 | 256,valmoro lona j,124 258 | 257,valmoroli@state.gov,124 259 | 258,valmorolj@state.gov,124 260 | 259,walmoro lona j,124 261 | 260,long term strategy group,125 262 | 261,diamond louise,126 263 | 262,cue lourdes c,127 264 | 263,g/tip:cdebaca luis,128 265 | 264,luzzatto,129 266 | 265,lynn,130 267 | 266,albright m k,131 268 | 267,albright madeleine,132 269 | 268,williamsbarrett,133 270 | 269,calivis maria,134 271 | 270,otero maria,135 272 | 271,oterom2@state.gov,135 273 | 272,af/pdpa:scott marianne,136 274 | 273,mark,137 275 | 274,markjpenn,138 276 | 275,mtorrey,139 277 | 276,eca:pally maura,140 278 | 277,pally maura m,140 279 | 278,baucus max,141 280 | 279,rooney megan,142 281 | 280,pverveer,143 282 | 281,vereer melanne s,143 283 | 282,verveer melanne e,143 284 | 283,verveer melanne s,143 285 | 284,verveerms@state.gov,143 286 | 285,fuchs michael h,144 287 | 286,fuchsmh@state.gov,144 288 | 287,posner michael h,145 289 | 288,posnermh@state.gov,145 290 | 289,bond michele t,146 291 | 290,michele.flournoy,147 292 | 291,rodriguez miguel e,148 293 | 292,mike,149 294 | 293,hanley monica r,150 295 | 294,hanleymr@state.gov,150 296 | 295,nhla,151 297 | 296,nancy,152 298 | 297,neera tanden,153 299 | 298,tandem neera,153 300 | 299,tanden neera,153 301 | 300,ntanden,153 302 | 301,new york times,154 303 | 302,norman nicholas,155 304 | 303,toiv nora f,156 305 | 304,toivnf@state.gov,156 306 | 305,tov nora f,157 307 | 306,opinion research,158 308 | 307,sanchez oscar arias,159 309 | 308,flores oscar,160 310 | 309,lores oscar,161 311 | 310,pvervee,162 312 | 311,kennedy patrick f,163 313 | 312,m:kennedy patrick f,163 314 | 313,collier paul,164 315 | 314,jones paul w,165 316 | 315,nea/ipa:knopf payton,166 317 | 316,robinson peter,167 318 | 317,crowley philip,168 319 | 318,crowley philip j,168 320 | 319,gordon philip h,169 321 | 320,gordon. philip h,169 322 | 321,gordonph@state.gov,169 323 | 322,pir,170 324 | 323,reines philipe i,170 325 | 324,reines philippe,170 326 | 325,reines philippe i,170 327 | 326,reines phillippe i,170 328 | 327,rines philippe i,170 329 | 328,preines,170 330 | 329,reines@state.gov,170 331 | 330,reinesp@state.gov,170 332 | 331,crowley phillip j,171 333 | 332,crowleypj@state.gov,171 334 | 333,campbell piper,172 335 | 334,prime minister,173 336 | 335,shah rajiv,174 337 | 336,rshah,174 338 | 337,recos,175 339 | 338,philippe reines,176 340 | 339,preval rene,177 341 | 340,lewis reta jo,178 342 | 341,holbrookerc@state.gov,179 343 | 342,verma richard,180 344 | 343,verma richard r,180 345 | 344,vermarr@state.gov,180 346 | 345,rsloan,181 347 | 346,blake robert o,182 348 | 347,danford robert a,183 349 | 348,hormats robert d,184 350 | 349,hormatsrd@state.gov,184 351 | 350,russo robert v,185 352 | 351,russo robert v,185 353 | 352,russorv@state.gov,185 354 | 353,rodriguezme@state.gov,186 355 | 354,howe rosemarie,187 356 | 355,rosemarie.howe,187 357 | 356,zaidi s akbar,188 358 | 357,s/srgia,189 359 | 358,state,190 360 | 359,berger samuel r,191 361 | 360,sberger,191 362 | 361,sandy,191 363 | 362,berger samuel,192 364 | 363,sgration,193 365 | 364,blumenthal sidney,194 366 | 365,sid,194 367 | 366,sbwhoeop,194 368 | 367,sbwhoeop@,194 369 | 368,sbwhoop,194 370 | 369,sir,195 371 | 370,talbott strobe,196 372 | 371,stalbott,196 373 | 372,stallbott,196 374 | 373,rice susan e,197 375 | 374,rice susan e.,197 376 | 375,grantham suzanne l,198 377 | 376,terry.duffy,199 378 | 377,donilon thomas e,200 379 | 378,nides thomas r,201 380 | 379,nidestr@state.gov,201 381 | 380,shannon thomas a,202 382 | 381,wha: shannon thomas a,202 383 | 382,shannonta@state.gov,202 384 | 383,tflourno,203 385 | 384,stern todd,204 386 | 385,stern todd d,204 387 | 386,stern todd d (s/secc),204 388 | 387,sterntd@state.gov,204 389 | 388,tillemann tomicah,205 390 | 389,tillemann tomicah s,205 391 | 390,tillemannts@state.gov,205 392 | 391,elbegdori tsakina,206 393 | 392,u.s. global leadership coalition,207 394 | 393,estados unidos da america,208 395 | 394,estados unidos de norteamerica,208 396 | 395,etatunis damerique,208 397 | 396,etatsunis damerique,208 398 | 397,united states of america,208 399 | 398,nuland victoria j,209 400 | 399,ebeling voda,210 401 | 400,ebelling voda,210 402 | 401,whadp,211 403 | 402,washington post,212 404 | 403,sherman wendy,213 405 | 404,sherman wendy r,213 406 | 405,wsherman,213 407 | 406,ilic werner x,214 408 | 407,white house,215 409 | 408,burns william j,216 410 | 409,burnswj@state.gov,216 411 | 410,wburns,216 412 | 411,wburns66,216 413 | 412,wburns66@,216 414 | 413,hubbard william,217 415 | 414,iscol zachary,218 416 | 415,aclb,219 417 | 416,alcb,220 418 | 417,l,221 419 | 418,latimes.com,222 420 | 419,mh.interiors,223 421 | 420,mhcaleja@state.gov,224 422 | 421,postmaster@state.gov,225 423 | 422,rooneym@state.gov,226 424 | 423,rrh.interiors,227 425 | 424,b6,228 426 | 425,sullivan jacob 1,87 427 | 426,mills cheryl 0,32 428 | 427,nuiand victoria j,229 429 | 428,reines philippe f,230 430 | 429,sullivan jacob j nuland victoria 1,231 431 | 430,sullivan jacobi,87 432 | 431,russorv@stategov,232 433 | 432,sullivan jacob .1 ‹sullivann@state.gov>,87 434 | 433,sullivan jacob i,87 435 | 434,burns strider,21 436 | 435,mcdonough denis r. (mailto: b6,87 437 | 436,sullivan jacob .1,87 438 | 437,abeclin huma,81 439 | 438,oscar flores,233 440 | 439,milts cheryl 0,32 441 | 440,sidney blumenthal,194 442 | 441,su ii iva gll@state.gov.,234 443 | 442,annemarie slaughter,10 444 | 443,sullivahu@state.gov,235 445 | 444,barton rick (cso),32 446 | 445,mills cheryl id,32 447 | 446,russoiv@state.gov,236 448 | 447,miliscd@stategov,237 449 | 448,sullivan jacob 3,87 450 | 449,abedin hume,81 451 | 450,hanky monica r,150 452 | 451,h ehrod17@clintonemailcom>,80 453 | 452,abedinh@stategov,238 454 | 453,lvlills cheryl d,32 455 | 454,tomlinson christina b3 cia pers/org,32 456 | 455,h ‹hrod17@clintonernail.com>,80 457 | 456,tanleyrnr@state.gov,239 458 | 457,hanleymr@stategov,240 459 | 458,hanley monica r .,150 460 | 459,sullivan jacob.),87 461 | 460,hemmen chris,32 462 | 461,rnillscd@state.gov,241 463 | 462,sullivan jacob .‹suilivan1j©st.ate.gov>,87 464 | 463,rnillscd@stategov.,242 465 | 464,sullivanjj@state.gov.,243 466 | 465,mills chey 0,32 467 | 466,reiriesp@state.gov,244 468 | 467,sidney blumenthal b6,194 469 | 468,suilivanii@stategov,245 470 | 469,sullivanj@state.gov,246 471 | 470,suilivanij@state.gok,247 472 | 471,hanleymr@state.gov.,248 473 | 472,reines philippe t,249 474 | 473,hanleyrnr@state.gov,250 475 | 474,h 1,80 476 | 475,hanieymr@state.gov,251 477 | 476,mills. cheryl 0,32 478 | 477,hanleymrgastategov,252 479 | 478,sulliyanfostate.gott,253 480 | 479,aliilscd@state.gov,254 481 | 480,sullivan jacob j esullivanii@stategov>,87 482 | 481,mills cheryl d :miliscd@stategov>,32 483 | 482,mills cheryl d [mailto:millscd@stategovi,80 484 | 483,mills cheryl d [mailto:millscd©state.gov],80 485 | 484,valmoro lona j ‹valmorou c stategov>,124 486 | 485,valnnoro lona j,124 487 | 486,mills cheryl 0emillscd@state.gov>,32 488 | 487,nidesth@stategoy,255 489 | 488,bums william j,216 490 | 489,h ‹hrod17@clintonemailcom>,80 491 | 490,millscd@state.gov.,256 492 | 491,jacob j sullivan,257 493 | 492,reines philippe),170 494 | 493,sullivan jacobj,87 495 | 494,jake sullivan _,87 496 | 495,sullivanji@state.gov,258 497 | 496,stevens john c,87 498 | 497,sullivanjj@state.golt,259 499 | 498,millscd@state.goy,260 500 | 499,nulandyj@state.goy,261 501 | 500,sulliyanij@state.goy,262 502 | 501,rnillscd@state.govs,263 503 | 502,nuland victoria 3,209 504 | 503,jake.sullivar,264 505 | 504,jilotylc@state.gov.,265 506 | 505,jake.sulliyan,266 507 | 506,michele.fl,267 508 | 507,cheryimills millscd@state.gov,268 509 | 508,jake.sulliva,269 510 | 509,valmoroll@state.gov.,270 511 | 510,habedin b6,271 512 | 511,valmorou@state.gov,272 513 | 512,filotylc@state.gov,273 514 | 513,habedin,274 515 | 514,cheryl.mills jake.sullivan,275 516 | 515,abedinh@state.gov.,276 517 | 516,millscd@state.aov,277 518 | 517,illotylc@state.gov,278 519 | 518,millscd@state ov,279 520 | 519,habedin(,280 521 | 520,doug band,281 522 | 521,sullivanij@state.gov.,282 523 | 522,preines@,283 524 | 523,abedinh state ov,284 525 | 524,cheryl.mills abedinh@state.gov,285 526 | 525,cheryl.mill,286 527 | 526,briar,287 528 | 527,abedinh@state.goy,288 529 | 528,a bedinh@state.gov,289 530 | 529,preine,290 531 | 530,valmorol.1@state.gov,291 532 | 531,sullivanij@state.gov,292 533 | 532,preines sullivanjj@state.gov b6,293 534 | 533,valmorolj@state.gov.,294 535 | 534,leltmanjd@state.gov,295 536 | 535,ullivanjj@state.gov,296 537 | 536,sta i bott,297 538 | 537,sullivanjj©state ov,298 539 | 538,millscd@state.00v.,299 540 | 539,steinbergib@state.gov,300 541 | 540,cheryl.millf.,301 542 | 541,mhcaleja@state.gove,302 543 | 542,cheryl.millsi,303 544 | 543,s abedinh@state.gov,304 545 | 544,valmorou@state.gov.,305 546 | 545,chetyl.mills sullivanij@state.gov,306 547 | 546,sullivanu@state.gov.,307 548 | 547,muscatinel@state.goy,308 549 | 548,preines sullivanjj@state.gov,309 550 | 549,axelrod_,310 551 | 550,wburns6,311 552 | 551,valmorol1@state.gov.,312 553 | 552,steinberg1b@state.gov,313 554 | 553,. huma abedin,314 555 | 554,abedinh@stategovl,315 556 | 555,valmorou©state.gov,316 557 | 556,reinesp@state.goy,317 558 | 557,sulliyanjj@state.goy,318 559 | 558,emillscd@state.gov,319 560 | 559,cheryl.mill sullivanjj@state.gov,320 561 | 560,cheryl.mills millscd@state.gov.,321 562 | 561,preines verveerms@state.gov,322 563 | 562,jilotylc@state.goy,323 564 | 563,val moro u@state.gov,324 565 | 564,a bed inh@state.gov,325 566 | 565,mot lc@state.gov,326 567 | 566,jilot lc@state. ov,327 568 | 567,.1ilotylc@state.gov.,328 569 | 568,iilotylc@state.gov.,329 570 | 569,jilotylc©state.gov.,330 571 | 570,cheryl.mills sullivanjj@state.gov,331 572 | 571,iewjj@state.gov,332 573 | 572,cheryl.mills _,333 574 | 573,sulliva njj@state.g ov,334 575 | 574,pverveel,335 576 | 575,. h,80 577 | 576,preines sullivanij@state.gov.,336 578 | 577,sta ibott,337 579 | 578,balderstonkm@state.gov.,338 580 | 579,11,80 581 | 580,rossdb@state.gov,339 582 | 581,bowens,340 583 | 582,jacobjlev,341 584 | 583,yeryeerms@state.goy,342 585 | 584,preines b6,343 586 | 585,valmorou@state.gove,344 587 | 586,abedinh@state.gove,345 588 | 587,campbelikm@state.gov,346 589 | 588,nancy millscd@state.gov b6,347 590 | 589,valmorou©state.gov.,348 591 | 590,andy manatos,80 592 | 591,vanbuskirk michael 1,349 593 | 592,huma abed in,350 594 | 593,caputo,351 595 | 594,.gordonph@state.gov.,352 596 | 595,preines sullivanjj@state.gov,353 597 | 596,cheryl.mills sullivanjj@state.gov b6,354 598 | 597,cheryl.mills( sullivanjj@state.gov,355 599 | 598,huma abedin b6,356 600 | 599,mtorrey1,357 601 | 600,glantz.gina,358 602 | 601,millscd@tate.gov,359 603 | 602,cheryl.mills huma abedin,360 604 | 603,cheryl.mills millscd@state.gov,361 605 | 604,campbelikm©state.gov,362 606 | 605,jacobjlew vermarr@state.gov,363 607 | 606,sullivanjj@state.gov b6,364 608 | 607,iilotylc@state.gov,365 609 | 608,rnillscd@state.gov.,366 610 | 609,sullivanjj@state.govr,367 611 | 610,lewij@state.gov,368 612 | 611,williamsbarrett millscd@state.gov.,369 613 | 612,abedinh©state.gov,370 614 | 613,s sullivanjj@state.gov,371 615 | 614,filotylc@state.gov.,372 616 | 615,..lilotylc@state.gov.,373 617 | 616,baer.danie,374 618 | 617,reines philippe i (pace),170 619 | 618,mills.cheryl d,32 620 | 619,millscd@state.ov,375 621 | 620,cmills,376 622 | 621,newmyer on behalf of jackie newmyer,85 623 | 622,cheryl mills[,32 624 | 623,otero mildred (clinton),377 625 | 624,iewij@state.gov,378 626 | 625,abed in huma,81 627 | 626,jake sullivan,87 628 | 627,preines huma abedin,379 629 | 628,h.,80 630 | 629,ieltmanjd@state.gov.,380 631 | 630,valmoroll@state.gov,381 632 | 631,h [mailto:hdr22@clintonemail.com],32 633 | 632,ben kobren,80 634 | 633,todd stern,382 635 | 634,jonespw2@state.gov.,383 636 | 635,daniel.baer@,384 637 | 636,jonespw2@state.gov,385 638 | 637,cmarshal,386 639 | 638,sbwhoeop b6,387 640 | 639,jackie newmyer,85 641 | 640,pverveer b6,143 642 | 641,cheryl.mill abedin huma,388 643 | 642,lee feinstein,119 644 | 643,cheryl.mills b6,32 645 | 644,strobe talbott,196 646 | 645,berger samuel r.,191 647 | 646,abedin hurna,81 648 | 647,abed in hu ma,81 649 | 648,jeffrey l farrow,93 650 | 649,pvervee _,143 651 | 650,jeffrey farrow,93 652 | 651,eizenstat stuart,32 653 | 652,valmoro lona j walmorou@state.goy>,124 654 | 653,lew jacob i,389 655 | 654,steinberg james,390 656 | 655,rosemarie.howe h,391 657 | 656,abedin hu ma,81 658 | 657,sbwhoeor,194 659 | 658,esullivanjj@state.gov,392 660 | 659,cheryl.miils@ millscd@state.gov,393 661 | 660,millscd©state.gov,394 662 | 661,justin cooper,395 663 | 662,strobe talbott b6,196 664 | 663,valmoro lona 1,124 665 | 664,axelrod david m.,50 666 | 665,john podesta,100 667 | 666,eabedinh@state.gov,396 668 | 667,abedinh@state.govr,397 669 | 668,cheryl.mills@ millscd@state.gov.,398 670 | 669,williamsbarre0,399 671 | 670,lissa muscatine b6,122 672 | 671,minyon moore .,32 673 | 672,capricia penavic marshall,400 674 | 673,maggie williams,401 675 | 674,rosemarie howe,402 676 | 675,valmoro lona j walmorou@state.gov>,124 677 | 676,lewjj@state.gov.,403 678 | 677,wendy sherman,213 679 | 678,jim kennedy,404 680 | 679,jake.sullivan(,87 681 | 680,choilet derek h,56 682 | 681,cdm,405 683 | 682,axelrod david m. b6,50 684 | 683,wburns66 b6 i,216 685 | 684,donilon thomas e.,200 686 | 685,jacob lew,86 687 | 686,lou de baca g/tip,70 688 | 687,* abedin huma,81 689 | 688,pj,406 690 | 689,crowleyp state ov. preines,407 691 | 690,hume abedin,408 692 | 691,valmoro lona1,124 693 | 692,marciel scot a,409 694 | 693,0 mills cheryl d,32 695 | 694,.,410 696 | 695,smith daniel b,411 697 | 696,il,412 698 | 697,cheryl.mill1,413 699 | 698,jpier4,414 700 | 699,berger samuel r. b6,191 701 | 700,sbwhoeopc,194 702 | 701,sullivanii@state.govr,415 703 | 702,holbrooke richard c,416 704 | 703,verveer melanne s werveerms@state.gov>,143 705 | 704,cheryl.millsc,32 706 | 705,m.k albright,131 707 | 706,tauscher ellen 0,63 708 | 707,jake sullivar,87 709 | 708,gina glantz b6,73 710 | 709,voda ebeling,210 711 | 710,abedin huma eabedinh@state.gov>,81 712 | 711,lew jacob 1,86 713 | 712,sbwhoeop b61,194 714 | 713,info@mailva.evite.com,81 715 | 714,luzzatt,417 716 | 715,daniel baer,46 717 | 716,reta jo lewis special representative global intergovernmental affairs,178 718 | 717,daniel.bae,418 719 | 718,valmorou state. ov,419 720 | 719,vanbuskirk michael .3,420 721 | 720,edwards christopher (jakarta/pro),421 722 | 721,merten kenneth h,32 723 | 722,preine h,422 724 | 723,preines h,423 725 | 724,shah rajiv (aid/a),174 726 | 725,sbwhoeor.,194 727 | 726,williamsbarret,424 728 | 727,sullivanii@state.gov,425 729 | 728,hannah richert,426 730 | 729,ross alec j,427 731 | 730,sbwhoecip,194 732 | 731,sbwhoeopi,428 733 | 732,. sullivan jacobi,87 734 | 733,betsyebelin,16 735 | 734,sbwhoeor b6,194 736 | 735,doua band,429 737 | 736,daniel meron,180 738 | 737,adams david s,430 739 | 738,doug hattaway,431 740 | 739,mills; cheryl d,32 741 | 740,colby cooper,81 742 | 741,kritenbrink daniel j,432 743 | 742,cheryl mills b6,32 744 | 743,abdinh@state.gov,433 745 | 744,fareed zein,32 746 | 745,sawsanhassan1,434 747 | 746,stanton katie,435 748 | 747,h b6,436 749 | 748,blake robert 0,182 750 | 749,irussorv@state.gov,437 751 | 750,valmoro lona .1,438 752 | 751,valmorol1@state.gov,439 753 | 752,valmorou@state.goy,440 754 | 753,valmdrou@state.gov,441 755 | 754,dimartino kitty,442 756 | 755,waxman sharon l,443 757 | 756,jcooper,444 758 | 757,lgraham doug band,445 759 | 758,jai:e sullivan,446 760 | 759,crowley philip 1,168 761 | 760,crowley philip1,168 762 | 761,sullivanii@state.gov.,447 763 | 762,hume abed in,448 764 | 763,sbvvhoeop,194 765 | 764,berniertoth michelle,449 766 | 765,coley theodore r,450 767 | 766,c — cheryl mills,32 768 | 767,rice susan e (usun),197 769 | 768,bonnie klehr,451 770 | 769,ramamurthy,452 771 | 770,h i,453 772 | 771,eichensehr kristen e,454 773 | 772,hooke kathleen h,455 774 | 773,johnson clifton m,456 775 | 774,tones susan,457 776 | 775,townley stephen g,458 777 | 776,torres susan,459 778 | 777,abedinhuma,81 779 | 778,evergreen,460 780 | 779,lona valmoro,461 781 | 780,fl,462 782 | 781,elaine weiss,463 783 | 782,kevin m. okeefe,464 784 | 783,michael m. conway,465 785 | 784,lew jacobi,466 786 | 785,hai,467 787 | 786,holbrooke richard,87 788 | 787,harris jennifer m,468 789 | 788,p1r,170 790 | 789,pcharron,469 791 | 790,zachary iscol,218 792 | 791,jiloty lauren c dilotylc@state.gov>,116 793 | 792,preine5,470 794 | 793,samuel berger,192 795 | 794,laurenjiloty jilotylc@state.gov,471 796 | 795,laurenjiloty,472 797 | 796,ian1evqr@state.gov,473 798 | 797,jake sullivan b6,87 799 | 798,woodardew@state.gov,474 800 | 799,sullivan jacob),87 801 | 800,rshal,475 802 | 801,megan rooney,142 803 | 802,millscd@state. ov,476 804 | 803,jacobjle iewjj@state.gov b6,477 805 | 804,declan kelly,478 806 | 805,jake.sullivan b6,87 807 | 806,steinberg1b@state.gov.,479 808 | 807,jake.sullivan h,480 809 | 808,ogordonph@state.gov.,481 810 | 809,crowley @state. ov,482 811 | 810,sbwhoeo,483 812 | 811,steven.everts,80 813 | 812,sullivanij@state.gove,484 814 | 813,p rei n es,485 815 | 814,imuscatine huma abedin b6,486 816 | 815,tillemannts@state.gov.,487 817 | 816,sullivan jacob1,87 818 | 817,markjpenr,488 819 | 818,dad mom,489 820 | 819,vaimorou@state.gov,490 821 | 820,prein6,491 822 | 821,sullivanjj@state.goy,492 823 | 822,. vermarr@state.gov,493 824 | 823,sullivanjj@siate.gov,494 825 | 824,rina amiri,87 826 | 825,feldman daniel f,495 827 | 826,ruggiero frank 3,496 828 | 827,singh vikram,497 829 | 828,.filotylc@state.gov.,498 830 | 829,h hrod17@clintonemail.com>,80 831 | 830,bstrider mmoore,499 832 | 831,.1ilotylc@state.gov,500 833 | 832,abed inh@state.gov.,501 834 | 833,burns strider b6,21 835 | 834,jon davidson,502 836 | 835,aclb b6,220 837 | 836,iynn,503 838 | 837,a bed in h@state.gov,504 839 | 838,sullivan jacob.,87 840 | 839,scott gration,87 841 | 840,s_specialassistants,505 842 | 841,jake.sullivar preines,506 843 | 842,david brock,51 844 | 843,lanny j. davis,72 845 | 844,capriciamarshall huma abedin,507 846 | 845,jilotylc©state.gov,508 847 | 846,marshallcp@state.goy,509 848 | 847,sid blumenthal,510 849 | 848,monica.hanle,511 850 | 849,hanle mr@state.gov,512 851 | 850,ha nleym r@state.gov,513 852 | -------------------------------------------------------------------------------- /L4/pagerank/Persons.csv: -------------------------------------------------------------------------------- 1 | Id,Name 2 | 1,111th Congress 3 | 2,AGNA USEMB Kabul Afghanistan 4 | 3,AP 5 | 4,ASUNCION 6 | 5,Alec 7 | 6,Alex Dupuy 8 | 7,American Beverage Association 9 | 8,Andrew Mayock 10 | 9,Andrew Shapiro 11 | 10,Anne-Marie Slaughter 12 | 11,Anthony Lake 13 | 12,Arturo Valenzuela 14 | 13,Ban Ki-moon 15 | 14,Barack Obama 16 | 15,Barbara Mikulski 17 | 16,Betsy Ebeling 18 | 17,Bill Clinton 19 | 18,Biography 20 | 19,Bonnie Klehr 21 | 20,Brian Greenspun 22 | 21,Burns Strider 23 | 22,Capricia Marshall 24 | 23,Carlos Pascual 25 | 24,Caroline Adler 26 | 25,Case Button 27 | 26,Cecile Richards 28 | 27,Chad Weston 29 | 28,Charles Kiamie 30 | 29,Chelsea Clinton 31 | 30,Cherie Blair 32 | 31,Cheryl 33 | 32,Cheryl Mills 34 | 33,Chester Crocker 35 | 34,Christopher Butzgy 36 | 35,Christopher Edwards 37 | 36,Christopher Green 38 | 37,Christopher Hill 39 | 38,Claire Coleman 40 | 39,Colin Powell 41 | 40,Council on Foreign Relations 42 | 41,Courtney Beale 43 | 42,Craig Kelly 44 | 43,Daily Sun 45 | 44,Dana Hyde 46 | 45,Daniel 47 | 46,Daniel Baer 48 | 47,Daniel Inonye 49 | 48,Daniel Schwerin 50 | 49,Danielle Brian 51 | 50,David Axelrod 52 | 51,David Brock 53 | 52,David Garten 54 | 53,David Johnson 55 | 54,David Miliband 56 | 55,Department of State 57 | 56,Derek Chollet 58 | 57,Diane Reynolds 59 | 58,Donald 60 | 59,Doug Band 61 | 60,Doug Hattaway 62 | 61,E. Pelton 63 | 62,Elizabeth Drew 64 | 63,Ellen Tauscher 65 | 64,Eni Faleomavaega 66 | 65,Eric Woodard 67 | 66,Esther Brimmer 68 | 67,FINCA International 69 | 68,Foreign Affairs Magazine 70 | 69,G Wills 71 | 70,G. Lou de Bac 72 | 71,G. Wills 73 | 72,George Mitchell 74 | 73,Gina Glantz 75 | 74,Govenman Etazini 76 | 75,Haiti 77 | 76,Han Duk-soo 78 | 77,Harold Hongju Koh 79 | 78,Heintz 80 | 79,Hill 81 | 80,Hillary Clinton 82 | 81,Huma Abedin 83 | 82,Ian Kelly 84 | 83,J. Finkle 85 | 84,JAMA 86 | 85,Jackie Newmyer 87 | 86,Jacob Lew 88 | 87,Jake Sullivan 89 | 88,James McGovern 90 | 89,James Smith 91 | 90,James Steinberg 92 | 91,Jan Piercy 93 | 92,Janice Jacobs 94 | 93,Jeffrey Farrow 95 | 94,Jeffrey Feltman 96 | 95,Jennifer Robinson 97 | 96,Jim Hoagland 98 | 97,Jim Kennedy 99 | 98,Joanne Laszczych 100 | 99,John Olver 101 | 100,John Podesta 102 | 101,Johnnie Carson 103 | 102,Jonathan Prince 104 | 103,Joshua Daniel 105 | 104,Judith Kieffer 106 | 105,Judith McHale 107 | 106,Justin Cooper 108 | 107,KPK 109 | 108,Kabul LGF Request 110 | 109,Karl Eikenberry 111 | 110,KellyC@state.gov 112 | 111,Kent Conrad 113 | 112,Kris Balderston 114 | 113,Kurt Campbell 115 | 114,L. Rosenberger 116 | 115,LGraham 117 | 116,Lauren Jiloty 118 | 117,Laurie Rubiner 119 | 118,Lee Brown 120 | 119,Lee Feinstein 121 | 120,Linda Dewan 122 | 121,Lisa Caputo 123 | 122,Lissa Muscatine 124 | 123,Lois Quam 125 | 124,Lona Valmoro 126 | 125,Long Term Strategy Group 127 | 126,Louise Diamond 128 | 127,Lourdes Cue 129 | 128,Luis CdeBaca 130 | 129,Luzzatto 131 | 130,Lynn Forester de Rothschild 132 | 131,M. Albright 133 | 132,Madeleine Albright 134 | 133,Maggie Williams 135 | 134,Maria Calivis 136 | 135,Maria Otero 137 | 136,Marianne Scott 138 | 137,Mark Hyman 139 | 138,Mark Penn 140 | 139,Marty Torrey 141 | 140,Maura Pally 142 | 141,Max Baucus 143 | 142,Megan Rooney 144 | 143,Melanne Verveer 145 | 144,Michael Fuchs 146 | 145,Michael Posner 147 | 146,Michele Bond 148 | 147,Michele Flournoy 149 | 148,Miguel Rodriguez 150 | 149,Mike 151 | 150,Monica Hanley 152 | 151,NHLA 153 | 152,Nancy Parrish 154 | 153,Neera Tanden 155 | 154,New York Times 156 | 155,Nicholas Norman 157 | 156,Nora Toiv 158 | 157,Nora Tov 159 | 158,Opinion Research 160 | 159,Oscar Arias Sanchez 161 | 160,Oscar Flores 162 | 161,Oscar Lores 163 | 162,PVervee 164 | 163,Patrick Kennedy 165 | 164,Paul Collier 166 | 165,Paul Jones 167 | 166,Payton Knopf 168 | 167,Peter Robinson 169 | 168,Philip Crowley 170 | 169,Philip Gordon 171 | 170,Philippe Reines 172 | 171,Phillip Crowley 173 | 172,Piper Campbell 174 | 173,Prime Minister 175 | 174,Rajiv Shah 176 | 175,Recos 177 | 176,Reines Philippe 178 | 177,Rene Preval 179 | 178,Reta Jo Lewis 180 | 179,Richard Holbrooke 181 | 180,Richard Verma 182 | 181,Rick Sloan 183 | 182,Robert Blake 184 | 183,Robert Danford 185 | 184,Robert Hormats 186 | 185,Robert Russo 187 | 186,Rodriguez Miguel 188 | 187,Rosemarie Howe 189 | 188,S. Akbar Zaidi 190 | 189,SRGIA 191 | 190,STATE 192 | 191,"Samuel (""Sandy"") Berger" 193 | 192,Samuel Berger 194 | 193,Scott Gration 195 | 194,Sidney Blumenthal 196 | 195,Sir 197 | 196,Strobe Talbott 198 | 197,Susan Rice 199 | 198,Suzanne Grantham 200 | 199,Terry Duffy 201 | 200,Thomas Donilon 202 | 201,Thomas Nides 203 | 202,Thomas Shannon 204 | 203,Tina Flournoy 205 | 204,Todd Stern 206 | 205,Tomicah Tillemann 207 | 206,Tsakina Elbegdori 208 | 207,U.S. Global Leadership Coalition 209 | 208,United States of America 210 | 209,Victoria Nuland 211 | 210,Voda Ebeling 212 | 211,WHADP 213 | 212,Washington Post 214 | 213,Wendy Sherman 215 | 214,Werner Ilic 216 | 215,White House 217 | 216,William Burns 218 | 217,William Hubbard 219 | 218,Zachary Iscol 220 | 219,aclb 221 | 220,alcb 222 | 221,l 223 | 222,latimes.com 224 | 223,mh.interiors 225 | 224,mhcaleja@state.gov 226 | 225,postmaster@state.gov 227 | 226,rooneym@state.gov 228 | 227,rrh.interiors 229 | 228,b6 230 | 229,nuiand victoria j 231 | 230,reines philippe f 232 | 231,sullivan jacob j nuland victoria 1 233 | 232,russorv@stategov 234 | 233,oscar flores 235 | 234,su ii iva gll@state.gov. 236 | 235,sullivahu@state.gov 237 | 236,russoiv@state.gov 238 | 237,miliscd@stategov 239 | 238,abedinh@stategov 240 | 239,tanleyrnr@state.gov 241 | 240,hanleymr@stategov 242 | 241,rnillscd@state.gov 243 | 242,rnillscd@stategov. 244 | 243,sullivanjj@state.gov. 245 | 244,reiriesp@state.gov 246 | 245,suilivanii@stategov 247 | 246,sullivanj@state.gov 248 | 247,suilivanij@state.gok 249 | 248,hanleymr@state.gov. 250 | 249,reines philippe t 251 | 250,hanleyrnr@state.gov 252 | 251,hanieymr@state.gov 253 | 252,hanleymrgastategov 254 | 253,sulliyanfostate.gott 255 | 254,aliilscd@state.gov 256 | 255,nidesth@stategoy 257 | 256,millscd@state.gov. 258 | 257,jacob j sullivan 259 | 258,sullivanji@state.gov 260 | 259,sullivanjj@state.golt 261 | 260,millscd@state.goy 262 | 261,nulandyj@state.goy 263 | 262,sulliyanij@state.goy 264 | 263,rnillscd@state.govs 265 | 264,jake.sullivar 266 | 265,jilotylc@state.gov. 267 | 266,jake.sulliyan 268 | 267,michele.fl 269 | 268,cheryimills millscd@state.gov 270 | 269,jake.sulliva 271 | 270,valmoroll@state.gov. 272 | 271,habedin b6 273 | 272,valmorou@state.gov 274 | 273,filotylc@state.gov 275 | 274,habedin 276 | 275,cheryl.mills jake.sullivan 277 | 276,abedinh@state.gov. 278 | 277,millscd@state.aov 279 | 278,illotylc@state.gov 280 | 279,millscd@state ov 281 | 280,habedin( 282 | 281,doug band 283 | 282,sullivanij@state.gov. 284 | 283,preines@ 285 | 284,abedinh state ov 286 | 285,cheryl.mills abedinh@state.gov 287 | 286,cheryl.mill 288 | 287,briar 289 | 288,abedinh@state.goy 290 | 289,a bedinh@state.gov 291 | 290,preine 292 | 291,valmorol.1@state.gov 293 | 292,sullivanij@state.gov 294 | 293,preines sullivanjj@state.gov b6 295 | 294,valmorolj@state.gov. 296 | 295,leltmanjd@state.gov 297 | 296,ullivanjj@state.gov 298 | 297,sta i bott 299 | 298,sullivanjj©state ov 300 | 299,millscd@state.00v. 301 | 300,steinbergib@state.gov 302 | 301,cheryl.millf. 303 | 302,mhcaleja@state.gove 304 | 303,cheryl.millsi 305 | 304,s abedinh@state.gov 306 | 305,valmorou@state.gov. 307 | 306,chetyl.mills sullivanij@state.gov 308 | 307,sullivanu@state.gov. 309 | 308,muscatinel@state.goy 310 | 309,preines sullivanjj@state.gov 311 | 310,axelrod_ 312 | 311,wburns6 313 | 312,valmorol1@state.gov. 314 | 313,steinberg1b@state.gov 315 | 314,. huma abedin 316 | 315,abedinh@stategovl 317 | 316,valmorou©state.gov 318 | 317,reinesp@state.goy 319 | 318,sulliyanjj@state.goy 320 | 319,emillscd@state.gov 321 | 320,cheryl.mill sullivanjj@state.gov 322 | 321,cheryl.mills millscd@state.gov. 323 | 322,preines verveerms@state.gov 324 | 323,jilotylc@state.goy 325 | 324,val moro u@state.gov 326 | 325,a bed inh@state.gov 327 | 326,mot lc@state.gov 328 | 327,jilot lc@state. ov 329 | 328,.1ilotylc@state.gov. 330 | 329,iilotylc@state.gov. 331 | 330,jilotylc©state.gov. 332 | 331,cheryl.mills sullivanjj@state.gov 333 | 332,iewjj@state.gov 334 | 333,cheryl.mills _ 335 | 334,sulliva njj@state.g ov 336 | 335,pverveel 337 | 336,preines sullivanij@state.gov. 338 | 337,sta ibott 339 | 338,balderstonkm@state.gov. 340 | 339,rossdb@state.gov 341 | 340,bowens 342 | 341,jacobjlev 343 | 342,yeryeerms@state.goy 344 | 343,preines b6 345 | 344,valmorou@state.gove 346 | 345,abedinh@state.gove 347 | 346,campbelikm@state.gov 348 | 347,nancy millscd@state.gov b6 349 | 348,valmorou©state.gov. 350 | 349,vanbuskirk michael 1 351 | 350,huma abed in 352 | 351,caputo 353 | 352,.gordonph@state.gov. 354 | 353,preines sullivanjj@state.gov 355 | 354,cheryl.mills sullivanjj@state.gov b6 356 | 355,cheryl.mills( sullivanjj@state.gov 357 | 356,huma abedin b6 358 | 357,mtorrey1 359 | 358,glantz.gina 360 | 359,millscd@tate.gov 361 | 360,cheryl.mills huma abedin 362 | 361,cheryl.mills millscd@state.gov 363 | 362,campbelikm©state.gov 364 | 363,jacobjlew vermarr@state.gov 365 | 364,sullivanjj@state.gov b6 366 | 365,iilotylc@state.gov 367 | 366,rnillscd@state.gov. 368 | 367,sullivanjj@state.govr 369 | 368,lewij@state.gov 370 | 369,williamsbarrett millscd@state.gov. 371 | 370,abedinh©state.gov 372 | 371,s sullivanjj@state.gov 373 | 372,filotylc@state.gov. 374 | 373,..lilotylc@state.gov. 375 | 374,baer.danie 376 | 375,millscd@state.ov 377 | 376,cmills 378 | 377,otero mildred (clinton) 379 | 378,iewij@state.gov 380 | 379,preines huma abedin 381 | 380,ieltmanjd@state.gov. 382 | 381,valmoroll@state.gov 383 | 382,todd stern 384 | 383,jonespw2@state.gov. 385 | 384,daniel.baer@ 386 | 385,jonespw2@state.gov 387 | 386,cmarshal 388 | 387,sbwhoeop b6 389 | 388,cheryl.mill abedin huma 390 | 389,lew jacob i 391 | 390,steinberg james 392 | 391,rosemarie.howe h 393 | 392,esullivanjj@state.gov 394 | 393,cheryl.miils@ millscd@state.gov 395 | 394,millscd©state.gov 396 | 395,justin cooper 397 | 396,eabedinh@state.gov 398 | 397,abedinh@state.govr 399 | 398,cheryl.mills@ millscd@state.gov. 400 | 399,williamsbarre0 401 | 400,capricia penavic marshall 402 | 401,maggie williams 403 | 402,rosemarie howe 404 | 403,lewjj@state.gov. 405 | 404,jim kennedy 406 | 405,cdm 407 | 406,pj 408 | 407,crowleyp state ov. preines 409 | 408,hume abedin 410 | 409,marciel scot a 411 | 410,. 412 | 411,smith daniel b 413 | 412,il 414 | 413,cheryl.mill1 415 | 414,jpier4 416 | 415,sullivanii@state.govr 417 | 416,holbrooke richard c 418 | 417,luzzatt 419 | 418,daniel.bae 420 | 419,valmorou state. ov 421 | 420,vanbuskirk michael .3 422 | 421,edwards christopher (jakarta/pro) 423 | 422,preine h 424 | 423,preines h 425 | 424,williamsbarret 426 | 425,sullivanii@state.gov 427 | 426,hannah richert 428 | 427,ross alec j 429 | 428,sbwhoeopi 430 | 429,doua band 431 | 430,adams david s 432 | 431,doug hattaway 433 | 432,kritenbrink daniel j 434 | 433,abdinh@state.gov 435 | 434,sawsanhassan1 436 | 435,stanton katie 437 | 436,h b6 438 | 437,irussorv@state.gov 439 | 438,valmoro lona .1 440 | 439,valmorol1@state.gov 441 | 440,valmorou@state.goy 442 | 441,valmdrou@state.gov 443 | 442,dimartino kitty 444 | 443,waxman sharon l 445 | 444,jcooper 446 | 445,lgraham doug band 447 | 446,jai:e sullivan 448 | 447,sullivanii@state.gov. 449 | 448,hume abed in 450 | 449,berniertoth michelle 451 | 450,coley theodore r 452 | 451,bonnie klehr 453 | 452,ramamurthy 454 | 453,h i 455 | 454,eichensehr kristen e 456 | 455,hooke kathleen h 457 | 456,johnson clifton m 458 | 457,tones susan 459 | 458,townley stephen g 460 | 459,torres susan 461 | 460,evergreen 462 | 461,lona valmoro 463 | 462,fl 464 | 463,elaine weiss 465 | 464,kevin m. okeefe 466 | 465,michael m. conway 467 | 466,lew jacobi 468 | 467,hai 469 | 468,harris jennifer m 470 | 469,pcharron 471 | 470,preine5 472 | 471,laurenjiloty jilotylc@state.gov 473 | 472,laurenjiloty 474 | 473,ian1evqr@state.gov 475 | 474,woodardew@state.gov 476 | 475,rshal 477 | 476,millscd@state. ov 478 | 477,jacobjle iewjj@state.gov b6 479 | 478,declan kelly 480 | 479,steinberg1b@state.gov. 481 | 480,jake.sullivan h 482 | 481,ogordonph@state.gov. 483 | 482,crowley @state. ov 484 | 483,sbwhoeo 485 | 484,sullivanij@state.gove 486 | 485,p rei n es 487 | 486,imuscatine huma abedin b6 488 | 487,tillemannts@state.gov. 489 | 488,markjpenr 490 | 489,dad mom 491 | 490,vaimorou@state.gov 492 | 491,prein6 493 | 492,sullivanjj@state.goy 494 | 493,. vermarr@state.gov 495 | 494,sullivanjj@siate.gov 496 | 495,feldman daniel f 497 | 496,ruggiero frank 3 498 | 497,singh vikram 499 | 498,.filotylc@state.gov. 500 | 499,bstrider mmoore 501 | 500,.1ilotylc@state.gov 502 | 501,abed inh@state.gov. 503 | 502,jon davidson 504 | 503,iynn 505 | 504,a bed in h@state.gov 506 | 505,s_specialassistants 507 | 506,jake.sullivar preines 508 | 507,capriciamarshall huma abedin 509 | 508,jilotylc©state.gov 510 | 509,marshallcp@state.goy 511 | 510,sid blumenthal 512 | 511,monica.hanle 513 | 512,hanle mr@state.gov 514 | 513,ha nleym r@state.gov 515 | -------------------------------------------------------------------------------- /L4/pagerank/email_pagerank.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | # 用PageRank挖掘希拉里邮件中的重要任务关系 3 | import pandas as pd 4 | import networkx as nx 5 | import numpy as np 6 | from collections import defaultdict 7 | import matplotlib.pyplot as plt 8 | 9 | # 数据加载 10 | emails = pd.read_csv("./Emails.csv") 11 | # 读取别名文件 12 | file = pd.read_csv("./Aliases.csv") 13 | aliases = {} 14 | for index, row in file.iterrows(): 15 | aliases[row['Alias']] = row['PersonId'] 16 | # 读取人名文件 17 | file = pd.read_csv("./Persons.csv") 18 | persons = {} 19 | for index, row in file.iterrows(): 20 | persons[row['Id']] = row['Name'] 21 | 22 | # 针对别名进行转换 23 | def unify_name(name): 24 | # 姓名统一小写 25 | name = str(name).lower() 26 | # 去掉, 和@后面的内容 27 | name = name.replace(",","").split("@")[0] 28 | # 别名转换 29 | if name in aliases.keys(): 30 | return persons[aliases[name]] 31 | return name 32 | # 画网络图 33 | def show_graph(graph, type = 'spring_layout'): 34 | if type == 'spring_layout': 35 | # 使用Spring Layout布局，类似中心放射状 36 | positions=nx.spring_layout(graph) 37 | if type == 'circular_layout': 38 | # 使用Circular Layout布局，在一个圆环上均匀分布 39 | positions=nx.circular_layout(graph) 40 | 41 | # 设置网络图中的节点大小，大小与pagerank值相关，因为pagerank值很小所以需要*20000 42 | nodesize = [x['pagerank']*20000 for v,x in graph.nodes(data=True)] 43 | # 设置网络图中的边长度 44 | edgesize = [np.sqrt(e[2]['weight']) for e in graph.edges(data=True)] 45 | # 绘制节点 46 | nx.draw_networkx_nodes(graph, positions, node_size=nodesize, alpha=0.4) 47 | # 绘制边 48 | nx.draw_networkx_edges(graph, positions, edge_size=edgesize, alpha=0.2) 49 | # 绘制节点的label 50 | nx.draw_networkx_labels(graph, positions, font_size=10) 51 | # 输出希拉里邮件中的所有人物关系图 52 | plt.show() 53 | 54 | # 将寄件人和收件人的姓名进行规范化 55 | emails.MetadataFrom = emails.MetadataFrom.apply(unify_name) 56 | emails.MetadataTo = emails.MetadataTo.apply(unify_name) 57 | 58 | # 设置遍的权重等于发邮件的次数 59 | edges_weights_temp = defaultdict(list) 60 | for row in zip(emails.MetadataFrom, emails.MetadataTo, emails.RawText): 61 | temp = (row[0], row[1]) 62 | if temp not in edges_weights_temp: 63 | edges_weights_temp[temp] = 1 64 | else: 65 | edges_weights_temp[temp] = edges_weights_temp[temp] + 1 66 | 67 | print(edges_weights_temp) 68 | print('-'*100) 69 | # 转化格式 (from, to), weight => from, to, weight 70 | edges_weights = [(key[0], key[1], val) for key, val in edges_weights_temp.items()] 71 | 72 | # 创建一个有向图 73 | graph = nx.DiGraph() 74 | # 设置有向图中的路径及权重(from, to, weight) 75 | graph.add_weighted_edges_from(edges_weights) 76 | # 计算每个节点（人）的PR值，并作为节点的pagerank属性 77 | pagerank = nx.pagerank(graph) 78 | # 获取每个节点的pagerank数值 79 | pagerank_list = {node: rank for node, rank in pagerank.items()} 80 | # 将pagerank数值作为节点的属性 81 | nx.set_node_attributes(graph, name = 'pagerank', values=pagerank_list) 82 | # 画网络图 83 | show_graph(graph) 84 | 85 | # 将完整的图谱进行精简 86 | # 设置PR值的阈值，筛选大于阈值的重要核心节点 87 | pagerank_threshold = 0.005 88 | # 复制一份计算好的网络图 89 | small_graph = graph.copy() 90 | # 剪掉PR值小于pagerank_threshold的节点 91 | for n, p_rank in graph.nodes(data=True): 92 | if p_rank['pagerank'] < pagerank_threshold: 93 | small_graph.remove_node(n) 94 | # 画网络图 95 | show_graph(small_graph, 'circular_layout') 96 | -------------------------------------------------------------------------------- /L4/pagerank/networkx_pagerank.py: -------------------------------------------------------------------------------- 1 | # 使用networkX计算节点的pagerank 2 | import networkx as nx 3 | import matplotlib.pyplot as plt 4 | 5 | # 创建有向图 6 | G = nx.DiGraph() 7 | # 设置有向图的边集合 8 | edges = [("A", "B"), ("A", "C"), ("A", "D"), ("B", "A"), ("B", "D"), ("C", "A"), ("D", "B"), ("D", "C")] 9 | # 在有向图G中添加边集合 10 | for edge in edges: 11 | G.add_edge(edge[0], edge[1]) 12 | 13 | # 有向图可视化 14 | layout = nx.spring_layout(G) 15 | nx.draw(G, pos=layout, with_labels=True, hold=False) 16 | plt.show() 17 | 18 | # 计算简化模型的PR值 19 | pr = nx.pagerank(G, alpha=1) 20 | print("简化模型的PR值：", pr) 21 | 22 | # 计算随机模型的PR值 23 | pr = nx.pagerank(G, alpha=0.8) 24 | print("随机模型的PR值：", pr) -------------------------------------------------------------------------------- /L4/pagerank/pagerank_simulation.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | a = np.array([[0, 1/2, 1, 0], 3 | [1/3, 0, 0, 1/2], 4 | [1/3, 0, 0, 1/2], 5 | [1/3, 1/2, 0, 0]]) 6 | a_leak = np.array([[0, 0, 0, 1/2], 7 | [0, 0, 0, 1/2], 8 | [0, 1, 0, 0], 9 | [0, 0, 1, 0]]) 10 | 11 | a_sink = np.array([[0, 0, 0, 0], 12 | [1/2, 0, 0, 1], 13 | [0, 1, 1, 0], 14 | [1/2, 0, 0, 0]]) 15 | 16 | b = np.array([1/4, 1/4, 1/4, 1/4]) 17 | w = b 18 | 19 | def work(a, w): 20 | for i in range(100): 21 | w = np.dot(a, w) 22 | print(w) 23 | 24 | def random_work(a, w, n): 25 | d = 0.85 26 | for i in range(100): 27 | w = (1-d)/n + d*np.dot(a, w) 28 | print(w) 29 | 30 | #work(a, w) 31 | #random_work(a, w, 4) 32 | #random_work(a_leak, w, 4) 33 | #random_work(a_sink, w, 4) -------------------------------------------------------------------------------- /L4/scc/scc1.py: -------------------------------------------------------------------------------- 1 | # 计算强连通图 2 | import networkx as nx 3 | import matplotlib.pyplot as plt 4 | 5 | # 创建有向图 6 | G = nx.DiGraph() 7 | # 在图中添加点 8 | G.add_nodes_from(['a','b','c','d','e','f','g','h']) 9 | G.add_edges_from([('a','b'),('b','c'),('b','c'),('c','d'),('d','c'),\ 10 | ('e','a'),('b','e'),('b','f'),('e','f'),('f','g'),('g','f'),\ 11 | ('c','g'),('h','g'),('d','h'),('h','d')]) 12 | 13 | # 有向图可视化 14 | layout = nx.spring_layout(G) 15 | nx.draw(G, pos=layout, with_labels=True, hold=False) 16 | plt.show() 17 | for c in nx.strongly_connected_components(G): 18 | print(c) 19 | 20 | 21 | -------------------------------------------------------------------------------- /L4/team_cluster/team_cluster.py: -------------------------------------------------------------------------------- 1 | # coding: utf-8 2 | from sklearn.cluster import KMeans 3 | from sklearn import preprocessing 4 | import pandas as pd 5 | import numpy as np 6 | # 数据加载 7 | data = pd.read_csv('team_cluster_data.csv', encoding='gbk') 8 | train_x = data[["2019国际排名","2018世界杯排名","2015亚洲杯排名"]] 9 | kmeans = KMeans(n_clusters=3) 10 | # 规范化到 [0,1] 空间 11 | min_max_scaler=preprocessing.MinMaxScaler() 12 | train_x=min_max_scaler.fit_transform(train_x) 13 | #print(train_x) 14 | # kmeans 算法 15 | kmeans.fit(train_x) 16 | predict_y = kmeans.predict(train_x) 17 | # 合并聚类结果，插入到原数据中 18 | result = pd.concat((data,pd.DataFrame(predict_y)),axis=1) 19 | result.rename({0:u'聚类结果'},axis=1,inplace=True) 20 | print(result) 21 | # 将结果导出到CSV文件中 22 | #result.to_csv("team_cluster_result.csv") 23 | 24 | -------------------------------------------------------------------------------- /L4/team_cluster/team_cluster_data.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cystanford/Data_Analysis_with_Python/a33b965d98612031a0effe17a9c6da3a1eaefb5e/L4/team_cluster/team_cluster_data.csv -------------------------------------------------------------------------------- /L4/textrank/news.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cystanford/Data_Analysis_with_Python/a33b965d98612031a0effe17a9c6da3a1eaefb5e/L4/textrank/news.txt -------------------------------------------------------------------------------- /L4/textrank/news_textrank.py: -------------------------------------------------------------------------------- 1 | #-*- encoding:utf-8 -*- 2 | from textrank4zh import TextRank4Keyword, TextRank4Sentence 3 | import jieba 4 | 5 | text = '王者荣耀典韦连招是使用一技能+大招+晕眩+二技能+普攻。这套连招主要用于先手强开团，当发现对面走位失误或撤退不及时，我们就可以利用一技能的加速。此外配合大招减速留住对手，协同队友完成击杀。\ 6 | 当对方站位较集中时，我们同样可以利用“一技能+大招+晕眩”进行团控和吸收伤害。\ 7 | 在吸收伤害的同时我们还可以利二技能打出不错的输出。这套连招重要的是把握时机，要有一夫当关，万夫莫开之势。\ 8 | 缺点是一技能的强化普攻和解除控制的效果会被浪费。\ 9 | 连招二：大招+晕眩+二技能+普攻+一技能+普攻。\ 10 | 这套连招用于偷袭对手后排很是好用，利用草丛埋伏。\ 11 | 大招跳到对面身上。迅速晕眩对手，接着二技能继续减速对手，二技能命中后会提升典韦到极限攻速，这时不断普攻，接下来一般会遇到两种情况，当对手继续逃跑时，我们利用一技能加速追击对手，强化普攻击杀对手。\ 12 | 当对手用技能控住我们我们可以利用一技能解除控制，追击并完成击杀。' 13 | 14 | # 输出关键词，设置文本小写，窗口为2 15 | tr4w = TextRank4Keyword() 16 | tr4w.analyze(text=text, lower=True, window=3) 17 | print('关键词：') 18 | for item in tr4w.get_keywords(20, word_min_len=2): 19 | print(item.word, item.weight) 20 | 21 | 22 | # 输出重要的句子 23 | tr4s = TextRank4Sentence() 24 | tr4s.analyze(text=text, lower=True, source = 'all_filters') 25 | print('摘要：') 26 | # 重要性较高的三个句子 27 | for item in tr4s.get_key_sentences(num=3): 28 | # index是语句在文本中位置，weight表示权重 29 | print(item.index, item.weight, item.sentence) 30 | -------------------------------------------------------------------------------- /L4/textrank/news_textrank_snownlp.py: -------------------------------------------------------------------------------- 1 | from snownlp import SnowNLP 2 | 3 | text = '王者荣耀典韦连招是使用一技能+大招+晕眩+二技能+普攻，这套连招主要用于先手强开团，当发现对面走位失误或撤退不及时，我们就可以利用一技能的加速，配合大招减速留住对手，协同队友完成击杀。\ 4 | 当对方站位较集中时，我们同样可以利用“一技能+大招+晕眩”进行团控和吸收伤害。\ 5 | 在吸收伤害的同时我们还可以利二技能打出不错的输出。这套连招重要的是把握时机，要有一夫当关，万夫莫开之势。\ 6 | 缺点是一技能的强化普攻和解除控制的效果会被浪费。\ 7 | 连招二：大招+晕眩+二技能+普攻+一技能+普攻。\ 8 | 这套连招用于偷袭对手后排很是好用，利用草丛埋伏。\ 9 | 大招跳到对面身上。迅速晕眩对手，接着二技能继续减速对手，二技能命中后会提升典韦到极限攻速，这时不断普攻，接下来一般会遇到两种情况，当对手继续逃跑时，我们利用一技能加速追击对手，强化普攻击杀对手。\ 10 | 当对手用技能控住我们我们可以利用一技能解除控制，追击并完成击杀。' 11 | snow = SnowNLP(text) 12 | # 打印关键词 13 | print(snow.keywords(20)) 14 | 15 | # TextRank算法 16 | print(snow.summary(3)) 17 | print(snow.sentiments) -------------------------------------------------------------------------------- /L4/textrank/sentence_textrank.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | import jieba 3 | import jieba.analyse 4 | import jieba.posseg as pseg 5 | 6 | sentence = '王者荣耀典韦连招是使用一技能+大招+晕眩+二技能+普攻，这套连招主要用于先手强开团，当发现对面走位失误或撤退不及时，我们就可以利用一技能的加速，配合大招减速留住对手，协同队友完成击杀。当对方站位较集中时，我们同样可以利用“一技能+大招+晕眩”进行团控和吸收伤害。在吸收伤害的同时我们还可以利二技能打出不错的输出。这套连招重要的是把握时机，要有一夫当关，万夫莫开之势。缺点是一技能的强化普攻和解除控制的效果会被浪费。' 7 | # 获取分词 8 | seg_list = jieba.cut(sentence, cut_all=False) 9 | print(' '.join(seg_list)) 10 | # 获取分词和词性 11 | words = pseg.cut(sentence) 12 | for word, flag in words: 13 | print('%s, %s' % (word, flag)) 14 | 15 | 16 | # 通过TF-IDF获取关键词 17 | keywords = jieba.analyse.extract_tags(sentence, topK=20, withWeight=True, allowPOS=('n','nr','ns')) 18 | for item in keywords: 19 | print(item[0],item[1]) 20 | print('-'*100) 21 | 22 | # 基于TextRank算法的关键词抽取 23 | #keywords = jieba.analyse.extract_tags(sentence, topK=20, withWeight=True, allowPOS=('n','nr','ns')) 24 | #keywords = jieba.analyse.textrank(sentence, topK=20, withWeight=True, allowPOS=('ns', 'n', 'vn', 'v')) 25 | #keywords = jieba.analyse.textrank(sentence, topK=20, withWeight=True, allowPOS=('n', 'ns')) 26 | keywords = jieba.analyse.textrank(sentence, topK=20, withWeight=True) 27 | print(keywords) 28 | for item in keywords: 29 | print(item[0],item[1]) 30 | -------------------------------------------------------------------------------- /L4/valid_tree/valid_tree.py: -------------------------------------------------------------------------------- 1 | # 判断一个图是否为树，使用DFS 2 | def valid_tree(n, edges): 3 | # 若这个图的边数比n-1多，那么一定有环，如果比n-1小，有孤立点 4 | if len(edges) != n - 1: 5 | return False 6 | 7 | # 初始化邻接表 8 | mat =[[] for i in range(n)] 9 | for i in range(len(edges)): 10 | v, u = edges[i][0], edges[i][1] 11 | mat[v].append(u) 12 | mat[u].append(v) 13 | 14 | # 判定这棵树的连通分量是否为1 15 | count = 0 16 | visit = [0 for i in range(n)] 17 | for i in range(n): 18 | if visit[i] == 0: 19 | dfs(i, visit, mat) 20 | # 统计连通图的个数 21 | count = count + 1 22 | 23 | if count > 1: 24 | return False 25 | return True 26 | 27 | # 深度优先遍历 28 | def dfs(node, visit, mat): 29 | # 访问过的节点不再进行访问 30 | visit[node] = 1 31 | for i in range(len(mat[node])): 32 | neighbor = mat[node][i] 33 | if visit[neighbor] == 0: 34 | dfs(neighbor, visit, mat) 35 | 36 | print(valid_tree(5, [[0,1], [0,2], [0,3], [1,4]])) 37 | print(valid_tree(5, [[0,1], [1,2], [2,3], [1,3], [1,4]])) 38 | -------------------------------------------------------------------------------- /L4/valid_tree/valid_tree2.py: -------------------------------------------------------------------------------- 1 | # 判断一个图是否为树，使用并查集 2 | 3 | # 查找帮主 4 | def find(x, parent): 5 | if parent[x] == x: 6 | return x 7 | return find(parent[x], parent); 8 | 9 | # 将y作为x的父亲节点 10 | def union(x, y, parent): 11 | parent[x] = y 12 | 13 | # 判断一个图是否为树 14 | def valid_tree(n, edges): 15 | # 初始化节点的父亲节点 16 | parent = [0 for i in range(n)] 17 | for i in range(n): 18 | parent[i] = i 19 | 20 | for edge in edges: 21 | p1 = find(edge[0], parent) 22 | p2 = find(edge[1], parent) 23 | # 两个节点的帮主相等，则说明存在环 24 | if p1 == p2: 25 | return False 26 | # p1是p2的父亲 27 | union(p2, p1, parent) 28 | 29 | # 如果连通分量为1，那么这些点的帮主都是同一个 30 | p = find(0, parent) 31 | for i in range(1,n): 32 | if p != find(i, parent): 33 | return False 34 | return True 35 | 36 | print(valid_tree(5, [[0,1], [0,2], [0,3], [1,4]])) 37 | print(valid_tree(5, [[0,1], [1,2], [2,3], [1,3], [1,4]])) 38 | --------------------------------------------------------------------------------