資料結構2

pandas data frame
還記得 dict 這個資料結構嗎？
將一個 dict 的資料結構轉換為 data frame 是最方便的方法

import pandas as pd # 引用套件並縮寫為 

pd name = ["Monkey D. Luffy", "Roronoa Zoro", "Nami", "Usopp", "Vinsmoke Sanji", "Tony Tony Chopper", "Nico Robin", "Franky", "Brook"] 

age = [19, 21, 20, 19, 21, 17, 30, 36, 90] 

straw_hat_dict = {"name": name, "age": age }

straw_hat_dict_df = pd.DataFrame(straw_hat_dict)

print(type(straw_hat_dict_df))

print(straw_hat_dict_df.dtypes)

straw_hat_dict_df

out:
<class 'pandas.core.frame.DataFrame'>

age      int64
name    object
dtype: object

	age	name
0	19	Monkey D. Luffy
1	21	Roronoa Zoro
2	20	Nami
3	19	Usopp
4	21	Vinsmoke Sanji
5	17	Tony Tony Chopper
6	30	Nico Robin
7	36	Franky
8	90	Brook

ps. 索引值起始是0

包含多種資料類型，不會像 ndarray 僅容納單一資料類型

import pandas as pd # 引用套件並縮寫為 pd

name = ["Monkey D. Luffy", "Roronoa Zoro", "Nami", "Usopp", "Vinsmoke Sanji", "Tony Tony Chopper", "Nico Robin", "Franky", "Brook"]

age = [19, 21, 20, 19, 21, 17, 30, 36, 90]

is_male = [True, True, False, True, True, True, False, True, True]

straw_hat_dict = {"name": name,

                  "age": age,

                  "is_male": is_male

}

straw_hat_df = pd.DataFrame(straw_hat_dict)

print(straw_hat_df.ix[0, :]) # 選第一個觀測值

print("---")

print(straw_hat_df.ix[:, "name"]) # 選第一欄

print("---")

print(straw_hat_df.ix[0, "name"]) # 選第一個觀測值的第一欄

print("---")

straw_hat_df

out:

age 19 i

s_male True name Monkey D. Luffy 

Name: 0, dtype: object --- 0 Monkey D. Luffy 1 Roronoa Zoro 2 Nami 3 Usopp 4 Vinsmoke Sanji 5 Tony Tony Chopper 6 Nico Robin 7 Franky 8 Brook Name: name, dtype: object --- Monkey D. Luffy ---

Out[46]:

	age	is_male	name
0	19	True	Monkey D. Luffy
1	21	True	Roronoa Zoro
2	20	False	Nami
3	19	True	Usopp
4	21	True	Vinsmoke Sanji
5	17	True	Tony Tony Chopper
6	30	False	Nico Robin
7	36	True	Franky
8	90	True	Brook

import pandas as pd # 引用套件並縮寫為 pd


name = ["Monkey D. Luffy", "Roronoa Zoro", "Nami", "Usopp", "Vinsmoke Sanji", "Tony Tony Chopper", "Nico Robin", "Franky", "Brook"]
age = [19, 21, 20, 19, 21, 17, 30, 36, 90]
is_male = [True, True, False, True, True, True, False, True, True]


straw_hat_dict = {"name": name,
"age": age,
"is_male": is_male
}


straw_hat_df = pd.DataFrame(straw_hat_dict)


filter_gender = straw_hat_df.ix[:, "is_male"] <= False
filter_age = straw_hat_df.ix[:, "age"] <= 30
straw_hat_df[filter_gender & filter_age]

out:

	age	is_male	name
2	20	False	Nami
6	30	False	Nico Robin

data frame 的概觀

import pandas as pd # 引用套件並縮寫為 pd

name = ["Monkey D. Luffy", "Roronoa Zoro", "Nami", "Usopp", "Vinsmoke Sanji", "Tony Tony Chopper", "Nico Robin", "Franky", "Brook"]

age = [19, 21, 20, 19, 21, 17, 30, 36, 90]

is_male = [True, True, False, True, True, True, False, True, True]

straw_hat_dict = {"name": name,

                  "age": age,

                  "is_male": is_male

}

straw_hat_df = pd.DataFrame(straw_hat_dict)


print(straw_hat_df.shape) # 回傳列數與欄數
print("---")
print(straw_hat_df.describe()) # 回傳描述性統計
print("---")
print(straw_hat_df.head(3)) # 回傳前三筆觀測值
print("---")
print(straw_hat_df.tail(3)) # 回傳後三筆觀測值
print("---")
print(straw_hat_df.columns) # 回傳欄位名稱
print("---")
print(straw_hat_df.index) # 回傳索引值