{"id":511,"date":"2019-07-06T23:16:00","date_gmt":"2019-07-06T15:16:00","guid":{"rendered":"http:\/\/note.systw.net\/note\/?p=511"},"modified":"2023-11-03T23:18:39","modified_gmt":"2023-11-03T15:18:39","slug":"python-pandas-access","status":"publish","type":"post","link":"https:\/\/systw.net\/note\/archives\/511","title":{"rendered":"Python pandas access"},"content":{"rendered":"\n

\u63a7\u5236dataframe<\/p>\n\n\n\n

……………………………………<\/p>\n\n\n\n

\u5916\u90e8\u8cc7\u6599\u8b80\u53d6\u8207\u5beb\u5165<\/strong><\/h2>\n\n\n\n

\u8b80\u6a94<\/strong>
pd.read_csv()
ex:
#cat data.csv
date,value
2016,100
2015,90
2014,50
>>>data=pd.read_csv(‘data.csv’)
>>>data.date
0 2016
1 2015
2 2014
ex:
pd.read_csv(‘ch09\/stock_px.csv’, parse_dates=True, index_col=0)
ex:
temp_df = pd.read_csv(‘file.csv’, header=None, names=[‘FileID’, ‘CustomerID’, ‘QueryTS’, ‘ProductID’])<\/p>\n\n\n\n


\u5132\u5b58<\/strong>
pd.to_csv()
ex:
pd.to_csv(“analysis_result.csv”)<\/p>\n\n\n\n

……………………………………<\/p>\n\n\n\n

\u8cc7\u6599\u8f49\u63db<\/strong><\/h2>\n\n\n\n

\u8f49\u63db
pandas to series<\/strong>
.series()
ex:
ts = pd.Series(df[‘Value’].values, index=df[‘Date’])<\/p>\n\n\n\n

pandas to numpy<\/strong>
.values
ex:
npdata=df.values<\/p>\n\n\n\n

pandas to list<\/strong>
.to_list()
ex:
listdata=df.to_list()<\/p>\n\n\n\n

dict to pandas<\/strong>
ex:
groups = [“Web”, “Dev”, “Cloud”, “Data”, “Security”, “group_p”]
groupvalue = [5, 9, 1, 4, 6, 7]
data_dict = {“groups”: groups,”value”: groupvalue}
data_df = pd.DataFrame(data_dict)<\/p>\n\n\n\n

list to pandas<\/strong>
ex:
listfieldlen = [59, 9, 19, 14, 6, 77]
df_fieldcount = pd.DataFrame()
df_fieldcount[‘fieldcount’]=listfieldlen
ex:
listfieldlen = [59, 9, 19, 14, 6, 77]
df_listfieldlen = pd.DataFrame(listfieldlen)<\/p>\n\n\n\n

refer
https:\/\/ithelp.ithome.com.tw\/articles\/10185922<\/p>\n\n\n\n

……………………….<\/p>\n\n\n\n

\u8cc7\u6599\u64cd\u4f5c<\/strong><\/h2>\n\n\n\n


\u8a2d\u5b9a\u6b04\u4f4d\u578b\u5225<\/strong>
.astype( < type> )
ex:
df[“Department”] =df[“Department”].astype(“category”)<\/p>\n\n\n\n

\u522a\u9664\u6307\u5b9a\u7684\u6b04\u4f4d<\/strong>
.drop( < field name > )
ex:
data=data.drop(data.columns[0],axis=1)
data=data.drop(“column name”,axis=1)
ex:
#\u522a\u9664\u6307\u5b9a\u6b04\u4f4d
> datatrain.drop([‘agenttime’],axis=1,inplace=True)<\/p>\n\n\n\n


\u5206\u5272\u6b04\u4f4d\u8cc7\u6599<\/strong>
.str.split( < char> )
ex:
data3[‘URL’].str.split(‘?’, expand=True)<\/p>\n\n\n\n

\u5408\u4f75\u6b04\u4f4d<\/strong>
#\u900f\u904e\u5408\u4f75\u6b04\u4f4d\u5efa\u7acb\u65b0\u6b04\u4f4d
ex:
> datatrain[\u2018ip’] = datatrain[\u2018ipv4′] + datatrain[\u2018ipv6′]<\/p>\n\n\n\n

\u4ee5\u7d2f\u7a4d\u65b9\u5f0f\u5408\u4f75\u8cc7\u6599<\/strong>
.append()
ex:
datatrain=train1.append(train2, ignore_index=True)<\/p>\n\n\n\n


\u6c34\u5e73\u5408\u4f75
<\/strong>.concat
ex:
datanew = pd.concat([data1,data2],axis=1, join_axes=[data1.index])<\/p>\n\n\n\n

… <\/p>\n\n\n\n

\u5c07\u7a7a\u503c(NaN)\u88dc0<\/strong>
.fillna()
ex:
df.fillna(0)
ex:
# \u5c07\u7a7a\u503c\u88dc\u6eff
> datatrain[\u2018account’].fillna(“null”, inplace=True)<\/p>\n\n\n\n

\u53d6\u4ee3<\/strong>
.replace()
\u6b64\u65b9\u6cd5\u9700\u5148\u900f\u904edictionary\u5c07\u5b57\u4e32\u8b8a\u6210\u4ee3\u865f
ex:
> dict_content={‘Tcp’:0,’TCP’:0,’udp’:1,’UDP’:1}
> datatrain[\u2018protocol’].replace(dict_content,regex=True)<\/p>\n\n\n\n

\u5c07\u8cc7\u6599\u524d\u5f8c\u7a7a\u767d\u522a\u9664<\/strong>
df.str.strip()<\/p>\n\n\n\n

\u8f49\u63db\u6642\u9593\u683c\u5f0f<\/strong>
to_datetime( < time>, format=” < time format>”)
ex:
pd.to_datetime(“6 Mar 2019 00:54:40”,format=’%d %b %Y %H:%M:%S’)
>2019-03-06 00:54:40<\/p>\n\n\n\n

…<\/p>\n","protected":false},"excerpt":{"rendered":"

\u63a7\u5236dataframe ……&#82 …<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"","fifu_image_alt":"","_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":false,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[14],"tags":[],"class_list":["post-511","post","type-post","status-publish","format-standard","hentry","category-develop"],"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/posts\/511","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/comments?post=511"}],"version-history":[{"count":0,"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/posts\/511\/revisions"}],"wp:attachment":[{"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/media?parent=511"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/categories?post=511"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/tags?post=511"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}