pandas入门——数据分组

数据分组

f = pd.read_csv("D://NBA.csv", encoding="gbk")
print(type(f))
print(f.shape)
# 按条件进行分组
g1 = f.groupby(by=list(["collage"]))
print(type(g1))
print(g1)

print(g1.first())

print(g1.size())

print(g1.describe())

print(g1.groups)

print(g1.get_group("University of Wisconsin"))

for name, group in g1:
print(name)
print("-".center(50, "-"))
print(group.shape)

print(g1.aggregate(numpy.sum))
print(g1.aggregate(numpy.mean))

print((g1.aggregate({"height": numpy.sum, "weight": numpy.mean})).rename(columns={"height": "求和", "weight": "平均数"}))