numpy数据处理

'''
Description: covid datasets显示
Autor: 365JHWZGo
Date: 2021-11-11 22:15:46
LastEditors: 365JHWZGo
LastEditTime: 2021-11-11 23:35:41
'''
import numpy as np

# 我们需要处理的脏数据
row_data = [
    ["Name", "StudentID", "Age", "AttendClass", "Score"],
    ["小明", 20131, 10, 1, 67],
    ["小花", 20132, 11, 1, 88],
    ["小菜", 20133, None, 1, "98"],
    ["小七", 20134, 8, 1, 110],
    ["花菜", 20134, 98, 0, None],
    ["刘欣", 20136, 12, 0, 12]
]
print('原始数据:\n',row_data)

# 将脏数据转化为numpy
data1 = np.array(row_data)
print('预处理的数据:\n',data1)

# 数据预处理
data_process = []
for i in range(len(row_data)):
    if i == 0:
        continue    # 不要首行字符串
    # 去掉首列名字
    data_process.append(row_data[i][1:])
data = np.array(data_process, dtype=np.float)
# print("data.dtype", data.dtype)
print('需要处理的部分数据:\n',data)

#清理数据

#判断是否有学号是重复的
sid = data[:, 0]
unique, counts = np.unique(sid, return_counts=True)
# print(unique)
# print(counts)
# print(unique[counts > 1])

#修改学号
data[4, 0] = 20135 
# print(data)

# #判断是否有None
# is_nan = np.isnan(data[:,1])
# print("is_nan:", is_nan)
# #找到该下标
# nan_idx = np.argwhere(is_nan)
# print(nan_idx)

# # 计算有数据的平均年龄，用 ~ 符号可以 True/False 对调
# mean_age = data[~np.isnan(data[:,1]), 1].mean()
# print("有数据的平均年龄：", mean_age)

# ~ 表示 True/False 对调，& 就是逐个做 Python and 的运算
normal_age_mask = ~np.isnan(data[:,1]) & (data[:,1] < 20)
# print("normal_age_mask:", normal_age_mask)

normal_age_mean = data[normal_age_mask, 1].mean()
# print("normal_age_mean:", normal_age_mean)

data[~normal_age_mask, 1] = normal_age_mean
# print("ages:", data[:, 1])

# 没上课的转成 nan
#data[data[:,2] == 0, 3]，先判断data[:,2] == 0，再将所有为True的行的第四个数据改为nan
data[data[:,2] == 0, 3] = np.nan

# 超过 100 分和低于 0 分的都处理一下
#超出100分和低于0分的话则为100或0
data[:, 3] = np.clip(data[:, 3], 0, 100)

# print(data[:, 2:])

afterData = np.array(data1, dtype=object)
for i in range(len(data)):
    afterData[i+1][1:] = data[i]
print('清理之后的数据:\n',afterData)