003.python科学计算库pandas(上)

约定不等于承诺〃 2021-10-06 15:16 408阅读 0赞

### 测试数据 [food\_info.csv][food_info.csv] ###

--------------------

### head ###

import pandas food_info = pandas.read_csv("food_info.csv") # csv文件类型 DataFrame print(type(food_info)) print("---1") # dtypes 返回每个列的数据类型。结果为字典 # food_info.dtypes['NDB_No'] 获取NDB_No列的数据类型 print(food_info.dtypes) print("---2") # head 返回第一个'n'行 ,缺省时n=5 first_rows = food_info.head(n=3) print(first_rows) print("---3") # columns 获取所有的列名称组成的索引元组 print(first_rows.columns) print("---4") # (3, 36) print(first_rows.shape)

![pycharm64_2018-09-14_11-24-33.png][]![pycharm64_2018-09-14_11-25-06.png][]

--------------------

### loc ###

import pandas food_info = pandas.read_csv("food_info.csv") # loc[i] 获取第i行的数据 结果为字典 food_info.loc[i]['columnName'] # 其中索引从0开始 print(food_info.loc[0]) # KeyError: 'the label [9999999] is not in the [index]' # print(food_info.loc[9999999])

![pycharm64_2018-09-14_11-32-31.png][]

import pandas food_info = pandas.read_csv("food_info.csv") # 返回一个DataFrame，其中包含索引3、4、5和6处的行 food_info.loc[3:6] # 返回一个DataFrame，其中包含索引2、5和10处的行。下面两种方法都可以。 two_five_ten = [2, 5, 10] food_info.loc[two_five_ten] food_info.loc[[2, 5, 10]]

--------------------

### column ###

import pandas food_info = pandas.read_csv("food_info.csv") ndb_col = food_info["NDB_No"] # 或者，可以通过传入字符串变量来访问列 col_name = "NDB_No" ndb_col = food_info[col_name] print(ndb_col)

![pycharm64_2018-09-14_11-39-51.png][]

import pandas food_info = pandas.read_csv("food_info.csv") columns = ["Zinc_(mg)", "Copper_(mg)"] zinc_copper = food_info[columns] # 跳过变量数组赋值 zinc_copper = food_info[["Zinc_(mg)", "Copper_(mg)"]] print(zinc_copper)

![mspaint_2018-09-14_11-44-38.png][]

--------------------

### tolist ###

import pandas food_info = pandas.read_csv("food_info.csv") # # columns 获取所有的列名称组成的索引元组 print(type(food_info.columns)) print(food_info.columns) # food_info.columns[0]='sadfaf' 类型错误(“索引不支持可变操作”) # tolist 返回值的列表 col_names = food_info.columns.tolist() col_names[0] = "sdfafg" print(col_names) print(type(col_names))

![pycharm64_2018-09-14_11-57-05.png][]

--------------------

### for ###

import pandas food_info = pandas.read_csv("food_info.csv") col_names = food_info.columns.tolist() gram_columns = [] for c in col_names: # 将列名称以(g)结尾的,添加进gram_columns列表 if c.endswith("(g)"): gram_columns.append(c) # 将gram_columns相关列读取到gram_df gram_df = food_info[gram_columns] # 读取gram_df的前3行数据 print(gram_df.head(3))

![pycharm64_2018-09-14_12-02-50.png][]

--------------------

### 列的算术运算 ###

import pandas import numpy food_info = pandas.read_csv("food_info.csv") iron_mg = food_info["Iron_(mg)"] print(iron_mg[0:3]) # 此列的每一行数据均除以1000 div_1000 = iron_mg / 1000 print(div_1000[0:3]) print() # 此列的每一行数据均加上100 add_100 = iron_mg + 100 print(add_100[0:3]) print() # 此列的每一行数据均减去50 sub_100 = iron_mg - 50 print(sub_100[0:3]) print() # 此列的每一行数据均乘以2 mult_2 = iron_mg * 2 print(mult_2[0:3]) # hstack上篇的连接方法 print(numpy.hstack((iron_mg[0:3], mult_2[0:3])).reshape(2, 3))

![pycharm64_2018-09-14_13-27-22.png][]

import pandas food_info = pandas.read_csv("food_info.csv") # 它将算术运算符应用于两列中的第一个值，两列中的第二个值，依此类推 print(food_info["Water_(g)"][0:3]) print(food_info["Energ_Kcal"][0:3]) print("-------------------------------") water_energy = food_info["Water_(g)"] * food_info["Energ_Kcal"] print(water_energy[0:3]) print("-------------------------------") iron_grams = food_info["Iron_(mg)"] / 1000 food_info["Iron_(g)"] = iron_grams print(food_info["Iron_(g)"][0:3])

![pycharm64_2018-09-14_13-34-01.png][]

import pandas food_info = pandas.read_csv("food_info.csv") # initial_rating = Protein_(g)列乘以2 减去 0.75乘以Lipid_Tot_(g)列 weighted_protein = food_info["Protein_(g)"] * 2 print(weighted_protein[0:3]) print("------------------------------") weighted_fat = -0.75 * food_info["Lipid_Tot_(g)"] print(weighted_fat[0:3]) print("------------------------------") initial_rating = weighted_protein + weighted_fat print(initial_rating[0:3])

![pycharm64_2018-09-14_13-39-27.png][]

--------------------

### max ###

import pandas food_info = pandas.read_csv("food_info.csv") # Energ_Kcal列上的最大值 max_calories = food_info["Energ_Kcal"].max() print(max_calories)

![pycharm64_2018-09-14_13-49-18.png][]

--------------------

### sort\_values ###

import pandas food_info = pandas.read_csv("food_info.csv") # 默认情况下，panda将按照我们按升序指定的列对数据进行排序，并返回一个新的DataFrame # 默认情况下，inplace=False 返回新的DataFrame # 默认情况下，ascending=True 按升序 # 默认情况下，kind=quicksort 使用快速排序算法 # 默认情况下，na_position=last NaN放在最后面 如果=first则放在最前面 # 对DataFrame进行就地排序，而不是返回新的DataFrame。 food_info.sort_values("Sodium_(mg)", inplace=True) print(food_info["Sodium_(mg)"][0:5]) # 按降序排序，而不是升序排序 food_info.sort_values("Sodium_(mg)", inplace=True, ascending=False) print(food_info["Sodium_(mg)"][0:5])

![pycharm64_2018-09-14_14-02-41.png][]

--------------------

[food_info.csv]: http://upyun.qubianzhong.cn/file/python_pandas/food_info.csv
[pycharm64_2018-09-14_11-24-33.png]: http://upyun.qubianzhong.cn/picture/pycharm64_2018-09-14_11-24-33.png
[pycharm64_2018-09-14_11-25-06.png]: http://upyun.qubianzhong.cn/picture/pycharm64_2018-09-14_11-25-06.png
[pycharm64_2018-09-14_11-32-31.png]: http://upyun.qubianzhong.cn/picture/pycharm64_2018-09-14_11-32-31.png
[pycharm64_2018-09-14_11-39-51.png]: http://upyun.qubianzhong.cn/picture/pycharm64_2018-09-14_11-39-51.png
[mspaint_2018-09-14_11-44-38.png]: http://upyun.qubianzhong.cn/picture/mspaint_2018-09-14_11-44-38.png
[pycharm64_2018-09-14_11-57-05.png]: http://upyun.qubianzhong.cn/picture/pycharm64_2018-09-14_11-57-05.png
[pycharm64_2018-09-14_12-02-50.png]: http://upyun.qubianzhong.cn/picture/pycharm64_2018-09-14_12-02-50.png
[pycharm64_2018-09-14_13-27-22.png]: http://upyun.qubianzhong.cn/picture/pycharm64_2018-09-14_13-27-22.png
[pycharm64_2018-09-14_13-34-01.png]: http://upyun.qubianzhong.cn/picture/pycharm64_2018-09-14_13-34-01.png
[pycharm64_2018-09-14_13-39-27.png]: http://upyun.qubianzhong.cn/picture/pycharm64_2018-09-14_13-39-27.png
[pycharm64_2018-09-14_13-49-18.png]: http://upyun.qubianzhong.cn/picture/pycharm64_2018-09-14_13-49-18.png
[pycharm64_2018-09-14_14-02-41.png]: http://upyun.qubianzhong.cn/picture/pycharm64_2018-09-14_14-02-41.png