def pd_dataframe():
data = {'state': ['Ohio', 'Ohio', 'Ohio', 'Nevada', 'Nevada'],
'year': [2000, 2001, 2002, 2001, 2002],
'pop': [1.5, 1.7, 3.6, 2.4, 2.9]}
frame=DataFrame(data)
print frame
print DataFrame(data,columns=['year','state','pop'])
frame2 = DataFrame(data, columns=['year', 'state', 'pop', 'debt'],index=['one', 'two', 'three', 'four', 'five'])
print frame2
print frame2['state']
print frame2.year
print frame2.ix['three']
frame2.debt=16.5
print frame2
frame2['debt']=np.arange(5.)
print frame2
val=Series(data=[-1.2,-1.5,-1.7],index=['two','four','five'])
frame2['debt']=val
print frame2
frame2['eastern']=frame2.state=='Ohio'
print frame2
del frame2['eastern']
print frame2.columns
# Name: first_name, dtype: object
print("\n")
print(df.loc[1]) # loc : index의 location 가지고 특정 위치의 데이터에 접근
print("\n")
print(df["age"].iloc[1:]) # iloc: index의 position
print("\n")
s = pd.Series(np.nan, index=[49,48,47,46,45,1,2,3,4,5]) # np.nan은 값을 NaN 으로
print(s)
print("\n")
print(s.iloc[3:]) # index의 위치가 3부터 출력
print("\n")
print(s.loc[:3]) # index가 3인 곳까지만 출력
print("\n")
print(df.age>40)
print("\n")
df.debt = df.age>40 # colum에 새로운 데이터 할당
print(df)
# first_name last_name age city debt
# 0 Jason Miller 42 San Francisco True
# 1 Molly Jacobson 52 Baltimore True
# 2 Tina Ali 36 Miami False
# 3 Jake Milner 24 Douglas False
# 4 Amy Cooze 73 Boston True
print("\n=======================================================\n")
values = Series(data=["M", "F", "F"], index=[0,1,3])
print(values)
print("\n")
df["sex"] = values # sex라는 column만들고 values에 할당된 index의 위치에 값들을 삽입
print(df)
print("\n")
df["first_name"] # 데이터 접근 df.loc[1] # loc: 특정 row 접근. index 의 이름을 기준 df.loc[1:2] df.iloc[1:] # index 순서를 기준 import numpy as np s = pd.Series(np.nan, index=[49, 48, 47, 46, 45, 1, 2, 3, 4, 5]) s.loc[:3] s.iloc[:3] df # 데이터 새로 할당 df.debt = df.age > 40 df df.T # transpose df.values df.to_csv() del df["debt"] df ## Selection & Drop df.head(3) df[["first_data", "age"]].head(3) df[:3] # column 없이 쓰는 경우는 row 기준
columns=['year', 'state', 'pop', 'debt'],
index=['one', 'two', 'three', 'four', 'five'])
frame2
# 2 ways to retrieve a column:
frame2['state']
frame2.year
## rows retrieval:
frame2.ix['three']
frame2[2:]
frame2['debt'] = np.arange(5)
frame2
val = Series([-1.2, -1.5, -1.7], index=['two', 'four', 'five'])
frame2.debt = val
frame2
frame2['eastern'] = frame2['state'] == 'Ohio'
frame2
## delete a column
del frame2['eastern']
frame2.columns
### passing nested dictionary to DataFrame:
pop = {
'Nevada': {
2001: 2.4,
2002: 2.9
},
frame2 = DataFrame(data,
columns=['year', 'state', 'pop', 'debt'],
index=['one', 'two', 'three', 'four', 'five'])
print(frame2)
print(frame2['state'])
print(frame2.year)
print("-------------")
print(frame2.iloc[1:3, :]) # 1到2行
print("-------------")
print(frame2.loc[['three', 'one']]) # 1到2行
##.ix is deprecated. Please use,.loc for label based indexing or,.iloc for positional indexing
print('2----------------')
frame2['debt'] = 16.5 # 修改一整列
print(frame2)
frame2.debt = np.arange(5) # 用numpy数组修改元素
print(frame2)
print()
print('用Series指定要修改的索引及其对应的值，没有指定的默认数据用NaN。')
val = Series([-1.2, -1.5, -1.7], index=['two', 'four', 'five'])
frame2['debt'] = val
print(frame2)
print()
print('赋值给新列')
frame2['eastern'] = (frame2.state == 'Ohio') # 如果state等于Ohio为True
print(frame2)
print(frame2.columns)
print()
def main():
# Series
# Series is likea 1d array.
lst = [4, 7, -5, 3]
obj = Series(lst)
print obj
print obj.values
print obj.index
obj2 = Series(copy.deepcopy(lst), index=['d', 'b', 'a', 'c'])
print obj2
print obj2.index
# numpy ndarray like
print obj2['a']
obj2['d'] = 6
print obj2[['c', 'a', 'd']]
print obj2
print obj2[obj2 > 0]
print obj2 * 2
print np.exp(obj2)
# dict like
print 'b' in obj2, 'e' in obj2
# dict to Series
sdata = {'Ohio': 35000, 'Texas': 71000, 'Oregon': 16000, 'Utah': 5000,}
obj3 = Series(sdata)
print obj3
# Value is NaN, if index not found.
states = ['Calfornia', 'Ohio', 'Oregon', 'Texas']
obj4 = Series(sdata, index=states)
print obj4
# Pandas function
print pd.isnull(obj4)
print pd.notnull(obj4)
# Series method
print obj4.isnull()
# Value is NaN, Index that does not exist only on one side
print obj3
print obj4
print obj3 + obj4
# Index name
obj4.name = 'population'
obj4.index.name = 'state'
print obj4
# Change index
obj4.index = ['a', 'b', 'c', 'd']
print obj4
# DataFrame
# DataFrame is like a spread sheet(table)
# DataFrame of Pandas are similar to R DataFrame
print '',''
data = {'state': ['Ohio', 'Ohio', 'Ohio', 'Nevada', 'Nevada'],
'year': [2000, 2001, 2002, 2001, 2002],
'pop': [1.5, 1.7, 3.6, 2.4, 2.9],}
frame = DataFrame(data)
print frame
# Order columns
print DataFrame(data, columns=['year', 'state', 'pop'])
# Columns, named indexes
# Column all value is NaN, if column not found in data
frame2 = DataFrame(data, columns=['year', 'state', 'pop', 'debt'],
index=['one', 'two', 'three', 'four', 'five'])
print frame2
print frame2.columns
print frame2['state']
print frame2.year
# row data
print frame2.ix['three']
# Change column value
frame2['debt'] = 16.5
print frame2.debt
frame2.debt = np.arange(5.) # error, size is not 5
print frame2.debt
# Column value is Nan, if index not found
val = Series([-1.2, -1.5, -1.7], index=['one', 'three', 'five'])
frame2.debt = val
print frame2
# new column. No frame.eastern
frame2['eastern'] = frame2.state == 'Ohio'
print frame2
# del column. No frame.eastern
del frame2['eastern']
print frame2
# nested dict to DataFrame
# outer key is column, and sorted
# inner key in index, and sorted
pop = {'Ohio':{2002: 3.6, 2000: 1.5, 2001:1.7},
'Nevada': {2001: 2.4, 2002:2.9},}
frame3 = DataFrame(pop)
print frame3
# transpose
print frame3.T
# DataFrame is not sorted, if specify index/columns
print DataFrame(pop, index=[2001, 2002, 2000], columns=['Ohio', 'Nevada'])
# Values method return ndarray, ndarray has one type
# return casted type, if ndarray has many type.
print frame3.values
print frame3.values.dtype
print frame2.values
print frame2.values.dtype
print frame2['year'].values.dtype
# Index Object(IntIndex, DateTimeIndex, PeriodIndex)
obj = Series(range(3), index='a b c'.split(' '))
index = obj.index
print type(index)
print index.dtype
# Index is immutable
try:
index[1] = 'd'
except:
print sys.exc_info()
print obj.index is pd.Index(['a', 'b', 'c'])
index = pd.Index(np.arange(3))
obj2 = Series(range(3), index=index)
print obj2.index is index
# Index as a Set
print frame3
print type(frame3.columns)
print 'Ohio' in frame3.columns
print 2003 in frame3.index
print index.append(pd.Index(['d']))
print index # result is true, immutable
# result # year 2002 # state good # pop 2.4 # debt NaN # Name: three, dtype: object # x['dept'] = 16.5 #修改整列数据 # result # year state pop debt dept # one 2000 ok 3.7 NaN 16.5 # two 2001 ok 3.6 NaN 16.5 # three 2002 good 2.4 NaN 16.5 # four 2003 bad 0.9 NaN 16.5 x.debt = n.arange(4) # 用numpy数组修改元素 # result # year state pop debt # one 2000 ok 3.7 0 # two 2001 ok 3.6 1 # three 2002 good 2.4 2 # four 2003 bad 0.9 3 val = Series([-1.2, -1.5, -1.7, 0], index=['one', 'two', 'four', 'six']) x.debt = val # 使用Series修改元素，DataFrme的行索引不变 # result # year state pop debt # one 2000 ok 3.7 -1.2 # two 2001 ok 3.6 -1.5 # three 2002 good 2.4 NaN # four 2003 bad 0.9 -1.7
data = {'state' : ['Ohio', 'Ohio', 'Ohio', 'Nevada', 'Nevada'],
'year' : [2000, 2001, 2002, 2001, 2002],
'pop' : [1.5, 1.7, 3.6, 2.4, 2.9]}
frame = DataFrame(data)
frame2 = DataFrame(data, columns=['year', 'state', 'pop', 'debt'],
index=['one', 'two', 'three', 'four', 'five'])
frame2['state']
frame2.values
frame2.year
frame2.ix['three']
frame2.ix[3]
frame2['debt'] = 16.5
#frame2['debt'] = [16.5, 17, 26]
frame2.debt = np.arange(5.)
val = Series([-1.2, -1.5, -1.7], index=['two', 'four', 'five'])
frame2.debt = val
frame2['eastern'] = frame2.state =='Ohio'
del frame2['eastern']
# dict of dicts into DataFrame
pop = {'Nevada': {2001: 2.5, 2002: 2.9}, 'Ohio': {2000: 1.5, 2001: 1.7, 2002: 3.6}}
frame3 = DataFrame(pop)
frame3.index.name = 'year'; frame3.columns.name = 'state'
frameTest = DataFrame(frame3)
frameTest = DataFrame(frame3, index=[1,2,3])
# pandas Index object
# In[29]: frame2.state # In[30]: frame2.year # In[31]: frame2.loc["three"] # In[32]: frame2.debt = np.arange(5) + 1 frame2 # In[33]: val = Series([-1.2, -1.5, -1.7], index=['two', 'three', 'five']) frame2.debt = val # In[34]: frame2 # In[35]: frame2['eastern'] = frame2.state == 'Ohio'
}
frame = DataFrame(data)
# print(frame)
# print(type(frame.year))
frame2 = DataFrame(data, columns=['year', 'state', 'pop'])
frame3 = DataFrame(data,
columns=['year', 'state', 'pop', 'debt'],
index=['one', 'two', 'three', 'four', 'five'])
# print(frame3['state'])
# print(frame3.state)
# print(frame3.ix['one'])
frame3.debt = 100
frame3.debt = np.arange(5.)
# print(np.arange(6.))
# print(type(np.arange(6.)))
temp_series = Series([-1.2, -1.5, -1.7], index=['two', 'four', 'five'])
frame3.debt = temp_series
frame3['ddd'] = np.nan
#추가할때나 지울때는 인덱스 형식으로 해야함 frame3.ddd 안됨
# print(frame3)
frame3['eastern'] = frame3.state == 'Ohio'
# print(frame3)
raw_data = {
'first_name': ['Jason', 'Molly', 'Tina', 'Jake', 'Amy'],
'last_name': ['Miller', 'Jacobson', 'Ali', 'Milner', 'Cooze'],
'age': [42, 52, 36, 24, 73],
'city': ['San Francisco', 'Baltimore', 'Miami', 'Douglas', 'Boston']
}
df = pd.DataFrame(raw_data, columns=['first_name', 'last_name', 'age', 'city'])
print(df)
print(DataFrame(raw_data, columns=['first_name', 'age']))
print(df.loc[1])
df_1 = DataFrame(raw_data,
columns=['first_name', 'last_name', 'age', 'city', 'debt'])
print(df_1)
df_1.debt = df_1.age > 40
print(df_1)
print(df_1.values)
print(df_1.to_csv())
print(df['first_name'].head(2))
print(df[['first_name', 'last_name']].head(2))
"""
data = {
'state': ['Ohio', 'Ohio', 'Ohio', 'Nevada', 'Nevada'],
'year': [2000, 2001, 2002, 2001, 2002],
'pop': [1.5, 1.7, 3.6, 2.4, 2.9]
}
frame = DataFrame(data)
frame
DataFrame(data, columns=['year', 'state', 'pop'])
frame2 = DataFrame(data,
columns=['year', 'state', 'pop', 'debt'],
index=['one', 'two', 'three', 'four', 'five'])
frame2['state']
frame2.year
frame2.ix['three']
frame2.debt = 16.5
frame2['debt'] = np.arange(5.)
frame2.debt = 'NaN'
val = Series([-1.2, -1.5, -1.7], index=['two', 'four', 'five'])
frame2['debt'] = val
frame2['eastern'] = frame2.state == 'Ohio'
del frame2['eastern']
frame2.columns
pop = {
'Nevada': {
2001: 2.4,
2002: 2.9
},
'Ohio': {
2000: 1.5,
2001: 1.7,
print(DataFrame(data))
print(DataFrame(data, columns=['year', 'state', 'pop'])) # designate order
print()
print("""## Designate index and column,
if column not exist, set 'NaN' in this column:""")
frame2 = DataFrame(data,
columns=['year', 'state', 'pop', 'debt'],
index=['one', 'two', 'three', 'four', 'five'])
print(frame2)
print(frame2['state'])
print(frame2.year)
print(frame2.ix['three'])
frame2['debt'] = 16.5 # modify the whole column using an element
print(frame2)
frame2.debt = np.arange(5) # modify the whole column using an array
print(frame2)
print()
print("""## Use Series to designate the index and value for modification,
the unspecified value set to 'NaN':""")
val = Series([-1.2, -1.5, -1.7], index=['two', 'four', 'five'])
frame2['debt'] = val
print(frame2)
print()
print("## Assign value to new column:")
frame2['eastern'] = (frame2.state == 'Ohio')
print(frame2)
print(frame2.columns)
'pop':[1.5, 1.7, 3.6, 2.4, 2.9]}
print DataFrame(data)
print DataFrame(data, columns = ['year', 'state', 'pop']) # 指定列顺序
print
print '指定索引，在列中指定不存在的列，默认数据用NaN。'
frame2 = DataFrame(data,
columns = ['year', 'state', 'pop', 'debt'],
index = ['one', 'two', 'three', 'four', 'five'])
print frame2
print frame2['state']
print frame2.year
print frame2.ix['three']
frame2['debt'] = 16.5 # 修改一整列
print frame2
frame2.debt = np.arange(5) # 用numpy数组修改元素
print frame2
print
print '用Series指定要修改的索引及其对应的值，没有指定的默认数据用NaN。'
val = Series([-1.2, -1.5, -1.7], index = ['two', 'four', 'five'])
frame2['debt'] = val
print frame2
print
print '赋值给新列'
frame2['eastern'] = (frame2.state == 'Ohio') # 如果state等于Ohio为True
print frame2
print frame2.columns
print
# five 2002 Nevada 2.9 NaN print(frame2.year) # one 2000 # two 2001 # three 2002 # four 2001 # five 2002 print(frame2.ix['three']) # 特定インデックス(ixで選択) # year 2002 # state Ohio # pop 3.6 # debt NaN frame2.debt = 16.5 print(frame2) # year state pop debt # one 2000 Ohio 1.5 16.5 # two 2001 Ohio 1.7 16.5 # three 2002 Ohio 3.6 16.5 # four 2001 Nevada 2.4 16.5 # five 2002 Nevada 2.9 16.5 frame2.debt = np.arange(5) print(frame2) # year state pop debt # one 2000 Ohio 1.5 0 # two 2001 Ohio 1.7 1 # three 2002 Ohio 3.6 2 # four 2001 Nevada 2.4 3
'pop': [1.5, 1.7, 3.6, 2.4, 2.9]
}
print DataFrame(data)
print DataFrame(data, columns=['year', 'state', 'pop'])
print
frame2 = DataFrame(data,
columns=['year', 'state', 'pop', 'debt'],
index=['one', 'two', 'three', 'four', 'five'])
print frame2
print frame2['state']
print frame2.year
print frame2.ix['three']
frame2['debt'] = 16.5
print frame2
frame2.debt = np.arange(5)
print frame2
print
val = Series([-1.2, -1.5, -1.7], index=['two', 'four', 'five'])
frame2['debt'] = val
print frame2
print
frame2['eastern'] = (frame2.state == 'Ohio')
print frame2
print frame2.columns
print
pop = {
'Nevada': {
'pop': [1.5, 1.7, 3.6, 2.4, 2.9]
}
frame = DataFrame(data)
frame2 = DataFrame(data,
columns=['year', 'state', 'pop', 'debt'],
index=['one', 'two', 'three', 'four', 'five'])
frame2['state']
frame2.values
frame2.year
frame2.ix['three']
frame2.ix[3]
frame2['debt'] = 16.5
#frame2['debt'] = [16.5, 17, 26]
frame2.debt = np.arange(5.)
val = Series([-1.2, -1.5, -1.7], index=['two', 'four', 'five'])
frame2.debt = val
frame2['eastern'] = frame2.state == 'Ohio'
del frame2['eastern']
# dict of dicts into DataFrame
pop = {
'Nevada': {
2001: 2.5,
2002: 2.9
},
'Ohio': {
2000: 1.5,
2001: 1.7,
2002: 3.6
