2018-11-30課程03

數(shù)據(jù)科學(xué)之3-3深入理解Series和DataFrame

import numpy as np
import pandas as pd
from pandas import Series, DataFrame

data = {'Country': ['Belgium', 'India', 'Brazil'],'Capital':['Brussles','New Delhi', 'Brasilia'],
       'Population':[111190846, 1303171035, 207847528]}

Series

s1 = pd.Series(data['Country'])
s1

0    Belgium
1      India
2     Brazil
dtype: object

s1.values

array(['Belgium', 'India', 'Brazil'], dtype=object)

s1.index

RangeIndex(start=0, stop=3, step=1)

DataFrame

df1 = pd.DataFrame(data)
df1

<div>
<style scoped>
.dataframe tbody tr th:only-of-type {
vertical-align: middle;
}

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>
<table border="1" class="dataframe">
<thead>
<tr style="text-align: right;">
<th></th>
<th>Country</th>
<th>Capital</th>
<th>Population</th>
</tr>
</thead>
<tbody>
<tr>
<th>0</th>
<td>Belgium</td>
<td>Brussles</td>
<td>111190846</td>
</tr>
<tr>
<th>1</th>
<td>India</td>
<td>New Delhi</td>
<td>1303171035</td>
</tr>
<tr>
<th>2</th>
<td>Brazil</td>
<td>Brasilia</td>
<td>207847528</td>
</tr>
</tbody>
</table>
</div>

df1.iterrows()

<generator object DataFrame.iterrows at 0x119af7af0>

for row in df1.iterrows():
    print(row), print(type(row))

(0, Country         Belgium
Capital        Brussles
Population    111190846
Name: 0, dtype: object)
<class 'tuple'>
(1, Country            India
Capital        New Delhi
Population    1303171035
Name: 1, dtype: object)
<class 'tuple'>
(2, Country          Brazil
Capital        Brasilia
Population    207847528
Name: 2, dtype: object)
<class 'tuple'>

DataFrame的IO操作

import webbrowser

link = "http://pandas.pydata.org/pandas-docs/version/0.20/io.html"
webbrowser.open(link)

True

df1 = pd.read_clipboard()

df1

<div>
<style scoped>
.dataframe tbody tr th:only-of-type {
vertical-align: middle;
}

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>
<table border="1" class="dataframe">
<thead>
<tr style="text-align: right;">
<th></th>
<th>Format Type</th>
<th>Data Description</th>
<th>Reader</th>
<th>Writer</th>
</tr>
</thead>
<tbody>
<tr>
<th>0</th>
<td>text</td>
<td>CSV</td>
<td>read_csv</td>
<td>to_csv</td>
</tr>
<tr>
<th>1</th>
<td>text</td>
<td>JSON</td>
<td>read_json</td>
<td>to_json</td>
</tr>
<tr>
<th>2</th>
<td>text</td>
<td>HTML</td>
<td>read_html</td>
<td>to_html</td>
</tr>
<tr>
<th>3</th>
<td>text</td>
<td>Local clipboard</td>
<td>read_clipboard</td>
<td>to_clipboard</td>
</tr>
<tr>
<th>4</th>
<td>binary</td>
<td>MS Excel</td>
<td>read_excel</td>
<td>to_excel</td>
</tr>
<tr>
<th>5</th>
<td>binary</td>
<td>HDF5 Format</td>
<td>read_hdf</td>
<td>to_hdf</td>
</tr>
<tr>
<th>6</th>
<td>binary</td>
<td>Feather Format</td>
<td>read_feather</td>
<td>to_feather</td>
</tr>
<tr>
<th>7</th>
<td>binary</td>
<td>Msgpack</td>
<td>read_msgpack</td>
<td>to_msgpack</td>
</tr>
<tr>
<th>8</th>
<td>binary</td>
<td>Stata</td>
<td>read_stata</td>
<td>to_stata</td>
</tr>
<tr>
<th>9</th>
<td>binary</td>
<td>SAS</td>
<td>read_sas</td>
<td></td>
</tr>
<tr>
<th>10</th>
<td>binary</td>
<td>Python Pickle Format</td>
<td>read_pickle</td>
<td>to_pickle</td>
</tr>
<tr>
<th>11</th>
<td>SQL</td>
<td>SQL</td>
<td>read_sql</td>
<td>to_sql</td>
</tr>
<tr>
<th>12</th>
<td>SQL</td>
<td>Google Big Query</td>
<td>read_gbq</td>
<td>to_gbq</td>
</tr>
</tbody>
</table>
</div>

# 復(fù)制一個(gè)12這個(gè)數(shù)字然后執(zhí)行這個(gè)語(yǔ)句 會(huì)把df1中的數(shù)據(jù)寫到粘貼板里
df1.to_clipboard()

df1.to_csv('df1.csv', index=False) # 去掉行索引

!ls

!more df1.csv

# 讀取 csv
df2 = pd.read_csv('df1.csv')
df2

<div>
<style scoped>
.dataframe tbody tr th:only-of-type {
vertical-align: middle;
}

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>
<table border="1" class="dataframe">
<thead>
<tr style="text-align: right;">
<th></th>
<th>Format Type</th>
<th>Data Description</th>
<th>Reader</th>
<th>Writer</th>
</tr>
</thead>
<tbody>
<tr>
<th>0</th>
<td>text</td>
<td>CSV</td>
<td>read_csv</td>
<td>to_csv</td>
</tr>
<tr>
<th>1</th>
<td>text</td>
<td>JSON</td>
<td>read_json</td>
<td>to_json</td>
</tr>
<tr>
<th>2</th>
<td>text</td>
<td>HTML</td>
<td>read_html</td>
<td>to_html</td>
</tr>
<tr>
<th>3</th>
<td>text</td>
<td>Local clipboard</td>
<td>read_clipboard</td>
<td>to_clipboard</td>
</tr>
<tr>
<th>4</th>
<td>binary</td>
<td>MS Excel</td>
<td>read_excel</td>
<td>to_excel</td>
</tr>
<tr>
<th>5</th>
<td>binary</td>
<td>HDF5 Format</td>
<td>read_hdf</td>
<td>to_hdf</td>
</tr>
<tr>
<th>6</th>
<td>binary</td>
<td>Feather Format</td>
<td>read_feather</td>
<td>to_feather</td>
</tr>
<tr>
<th>7</th>
<td>binary</td>
<td>Msgpack</td>
<td>read_msgpack</td>
<td>to_msgpack</td>
</tr>
<tr>
<th>8</th>
<td>binary</td>
<td>Stata</td>
<td>read_stata</td>
<td>to_stata</td>
</tr>
<tr>
<th>9</th>
<td>binary</td>
<td>SAS</td>
<td>read_sas</td>
<td></td>
</tr>
<tr>
<th>10</th>
<td>binary</td>
<td>Python Pickle Format</td>
<td>read_pickle</td>
<td>to_pickle</td>
</tr>
<tr>
<th>11</th>
<td>SQL</td>
<td>SQL</td>
<td>read_sql</td>
<td>to_sql</td>
</tr>
<tr>
<th>12</th>
<td>SQL</td>
<td>Google Big Query</td>
<td>read_gbq</td>
<td>to_gbq</td>
</tr>
</tbody>
</table>
</div>

df1.to_json()

'{"Format Type":{"0":"text","1":"text","2":"text","3":"text","4":"binary","5":"binary","6":"binary","7":"binary","8":"binary","9":"binary","10":"binary","11":"SQL","12":"SQL"},"Data Description":{"0":"CSV","1":"JSON","2":"HTML","3":"Local clipboard","4":"MS Excel","5":"HDF5 Format","6":"Feather Format","7":"Msgpack","8":"Stata","9":"SAS","10":"Python Pickle Format","11":"SQL","12":"Google Big Query"},"Reader":{"0":"read_csv","1":"read_json","2":"read_html","3":"read_clipboard","4":"read_excel","5":"read_hdf","6":"read_feather","7":"read_msgpack","8":"read_stata","9":"read_sas","10":"read_pickle","11":"read_sql","12":"read_gbq"},"Writer":{"0":"to_csv","1":"to_json","2":"to_html","3":"to_clipboard","4":"to_excel","5":"to_hdf","6":"to_feather","7":"to_msgpack","8":"to_stata","9":" ","10":"to_pickle","11":"to_sql","12":"to_gbq"}}'

pd.read_json(df1.to_json())

<div>
<style scoped>
.dataframe tbody tr th:only-of-type {
vertical-align: middle;
}

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

</style>
<table border="1" class="dataframe">
<thead>
<tr style="text-align: right;">
<th></th>
<th>Format Type</th>
<th>Data Description</th>
<th>Reader</th>
<th>Writer</th>
</tr>
</thead>
<tbody>
<tr>
<th>0</th>
<td>text</td>
<td>CSV</td>
<td>read_csv</td>
<td>to_csv</td>
</tr>
<tr>
<th>1</th>
<td>text</td>
<td>JSON</td>
<td>read_json</td>
<td>to_json</td>
</tr>
<tr>
<th>10</th>
<td>binary</td>
<td>Python Pickle Format</td>
<td>read_pickle</td>
<td>to_pickle</td>
</tr>
<tr>
<th>11</th>
<td>SQL</td>
<td>SQL</td>
<td>read_sql</td>
<td>to_sql</td>
</tr>
<tr>
<th>12</th>
<td>SQL</td>
<td>Google Big Query</td>
<td>read_gbq</td>
<td>to_gbq</td>
</tr>
<tr>
<th>2</th>
<td>text</td>
<td>HTML</td>
<td>read_html</td>
<td>to_html</td>
</tr>
<tr>
<th>3</th>
<td>text</td>
<td>Local clipboard</td>
<td>read_clipboard</td>
<td>to_clipboard</td>
</tr>
<tr>
<th>4</th>
<td>binary</td>
<td>MS Excel</td>
<td>read_excel</td>
<td>to_excel</td>
</tr>
<tr>
<th>5</th>
<td>binary</td>
<td>HDF5 Format</td>
<td>read_hdf</td>
<td>to_hdf</td>
</tr>
<tr>
<th>6</th>
<td>binary</td>
<td>Feather Format</td>
<td>read_feather</td>
<td>to_feather</td>
</tr>
<tr>
<th>7</th>
<td>binary</td>
<td>Msgpack</td>
<td>read_msgpack</td>
<td>to_msgpack</td>
</tr>
<tr>
<th>8</th>
<td>binary</td>
<td>Stata</td>
<td>read_stata</td>
<td>to_stata</td>
</tr>
<tr>
<th>9</th>
<td>binary</td>
<td>SAS</td>
<td>read_sas</td>
<td></td>
</tr>
</tbody>
</table>
</div>

df1.to_html('df.html')

df1.to_excel('df1.xlsx')
?著作權(quán)歸作者所有,轉(zhuǎn)載或內(nèi)容合作請(qǐng)聯(lián)系作者
【社區(qū)內(nèi)容提示】社區(qū)部分內(nèi)容疑似由AI輔助生成，瀏覽時(shí)請(qǐng)結(jié)合常識(shí)與多方信息審慎甄別。
平臺(tái)聲明：文章內(nèi)容（如有圖片或視頻亦包括在內(nèi)）由作者上傳并發(fā)布，文章內(nèi)容僅代表作者本人觀點(diǎn)，簡(jiǎn)書系信息發(fā)布平臺(tái)，僅提供信息存儲(chǔ)服務(wù)。

相關(guān)閱讀更多精彩內(nèi)容

友情鏈接更多精彩內(nèi)容