Python for Time Series Data Analysis (Udemy) 2

引き続きUdemyでPython for Time Series Data Analysisで、pandasの基礎の学習を進める。pandasライブラリの便利な関数を使えば、簡単にdataの整形ができそうだ。

pandasの学習コード4つ目

import pandas as pd
data = {'Company':['GOOG','GOOG','MSFT','MSFT','FB','FB'],'Person':['Sam','Charlie','Amy','Vanessa','Carl','Sarah'],'Sales':[200,120,340,124,243,350]}
df = pd.DataFrame(data)
df
df.groupby('Company').mean()
df.groupby('Company').describe().transpose()

pandasの学習コード5つ目

import pandas as pd
df = pd.DataFrame({'col1':[1,2,3,4],'col2':[444,555,666,444],'col3':['abc','def','ghi','xyz']})
df.head()
len(df['col2'].unique())
df['col2'].unique()
df['col2'].value_counts()
newdf = df[(df['col1'] > 2) & (df['col2'] == 444)]
newdf
def times_two(number):
    return number*2
df['new'] = df['col1'].apply(times_two)
del df['new']
df
df.columns
df.index
df.info()
df.describe()
df
df.sort_values('col2',ascending=False)

pandasの学習コード6つ目

import pandas as pd
pd.read_csv('example.csv')
df
newdf = df[['a','b']]
newdf.to_csv('mynew.csv',index=True)
pd.read_excel('Excel_Sample.xlsx',sheet_name='Sheet1')
df.columns
df.drop('Unnamed: 0',axis=1)
mylist_of_tables = pd.read_html('https://www.fdic.gov/bank/individual/failed/banklist.html')
type(mylist_of_tables)
len(mylist_of_tables)
df = mylist_of_tables[0]

pandasの学習コード7つ目

import pandas as pd
pd.read_csv('example.csv')
df
newdf = df[['a','b']]
newdf.to_csv('mynew.csv',index=True)
pd.read_excel('Excel_Sample.xlsx',sheet_name='Sheet1')
df.columns
df.drop('Unnamed: 0',axis=1)
mylist_of_tables = pd.read_html('https://www.fdic.gov/bank/individual/failed/banklist.html')
type(mylist_of_tables)
len(mylist_of_tables)
df = mylist_of_tables[0]