pandas的DataFrame的创建、增删改

gzj137070928

pandas的DataFrame的创建和增删改

import pandas as pd
import time

idx = [1,2,3,5,6,7,9,4,8]
name = ["apple","pearl","orange", "apple","orange","orange","apple","pearl","orange"]
price = [5.20,3.50,7.30,5.00,7.50,7.30,5.20,3.70,7.30]
N = 1  # 数据越大，内存差距越大
df = pd.DataFrame({ "fruit": name*N , "price" : price*N}, index = idx*N)
print (df,"\n")
print ('memory_usage',df.memory_usage(),"\n")
print (df.dtypes)
print ("*" * 20)
df['fruit'] = df['fruit'].astype('category')
# 将fruit列由Series改为了category类型,通过codes和categories组合出fruit的values
# 第二种创建方法：
# cat = pd.categorial(name)
# df['fruit'] = cat
print (df)
print ('memory_usage',df.memory_usage(),"\n")
print (df.dtypes)
print('fruit.values:',df.fruit.values)
print('fruit.values.codes:',df.fruit.values.codes)
print('fruit.values.categories:',df.fruit.values.categories)
# categories数据的修改
df.fruit.values.categories = ["Pearl", "Orange", "Apple"]
df.fruit.values.rename_categories(["Apple", "Orange", "Pearl"],inplace = True)
# categories数据的增加
df_new = pd.DataFrame({"fruit":["watermelon"] * 3, 
                       "price":[2.75, 2.60, 2.55]},
                       index = [11, 12, 13])
df.fruit.values.add_categories("watermelon", inplace = True)
df = df.append(df_new)
# 这里需要注意的是add_categories函数需要在插入数据之前调用，
# 否则数据增加进去了但是codes并未更新都是-1。
# 下面是删除categories
df = df[df.fruit != "apple"]  # 利用布尔选择删除了所有的"apple"的记录
df.fruit.values.remove_categories("apple", inplace = True)
# 删除了df的fruit这个categorical data的categories里的种类"apple"，如果注释掉此语句，codes则还是用原categories进行编码。
df.fruit.cat.remove_unused_categories(inplace = True)  # 删除未使用的categories
print('总的数据个数：',df.fruit.count())
print('categories分别出现的次数：',df.fruit.value_counts())