利用excel进行基础的excel数据分析,代码供自己日后学习及复查备用
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from scipy.stats import linregress
import seaborn as sns
students = pd.read_excel("./student.xlsx",index_col="id")
score = pd.read_excel("./student.xlsx",sheet_name="score",index_col="id")
# 联合两张工作表
table = students.join(score,how="left",on="id").fillna(0)
table.score = table.score.astype(int)
print(table)
# 分割数据
df = students["name"].str.split("_",expand = True)
students["name1"] = df[0].str.upper()
students["name2"] = df[1]
print(students)
# 统计分析(求和,求平均值,
temp = students[["test1", "test2", "test3"]]
students["row_total"] = temp.sum(axis=1)
students["row_average"] = temp.mean(axis=1)
col_mean = students[["test1", "t