mowareのブログ

python setup.py build --static-deps

python setup.py install

import pandas as pd

df = pd.read_excel('test.xlsx',sheet_name=0)
print(f"df:\n{df}\n")

df.set_index('分類',inplace=True)
print(f"dfインデックス設定後:\n{df}\n")

labels = ['A','B','C','D','E']
df2 = df.reindex(labels, axis=0)
print(f"df2:\n{df2}\n")

# 空データの分類Cを残すための処理
df3 = df2.replace({'NaN':0})
print(f"df3:\n{df3}\n")

df4 = df3.reset_index()
print(f"df4:\n{df4}\n")
--------------------------------------------------

出力
--------------------------------------------------
df:
  分類  評価額  取得額   損益
0  A  110  100   10
1  B  150  100   50
2  D  200  100  100
3  E  120  100   20

dfインデックス設定後:
    評価額  取得額   損益
分類               
A   110  100   10
B   150  100   50
D   200  100  100
E   120  100   20

df2:
      評価額    取得額     損益
分類                     
A   110.0  100.0   10.0
B   150.0  100.0   50.0
C     NaN    NaN    NaN
D   200.0  100.0  100.0
E   120.0  100.0   20.0

df3:
      評価額    取得額     損益
分類                     
A   110.0  100.0   10.0
B   150.0  100.0   50.0
C     NaN    NaN    NaN
D   200.0  100.0  100.0
E   120.0  100.0   20.0

df4:
  分類    評価額    取得額     損益
0  A  110.0  100.0   10.0
1  B  150.0  100.0   50.0
2  C    NaN    NaN    NaN
3  D  200.0  100.0  100.0
4  E  120.0  100.0   20.0

import time,datetime

start = time.time()

＜処理＞

# 処理時間算出(秒)
process_time = time.time() - start
td = datetime.timedelta(seconds = process_time).total_seconds()

# 小数点第２位まで表示
td_2f = f'{td:.2f}'

num = 123.456
print(f'{num:.1f}')
print(f'{num:.06f}')
--------------------------------------------------

出力
--------------------------------------------------
123.5
123.456000

# 代替スクリプト改良版

# 文字コードをUTF-8に変換してソース取り込み
html = driver.page_source.encode('utf-8')

# BeautifulSoupでデータ抽出
soup = BeautifulSoup(html, "html.parser")

# soupから３番目のtableを抽出
table = soup.find_all("table",attrs={"cellspacing" : "1"})[2]
rows = table.findAll("tr")

list_rows = []
for row in rows:
    list_row = []
    for cell in row.findAll(['td', 'th']):
        text = cell.get_text()
        text2 = text.replace('"','').replace("\n","").replace(" ","").replace("　","")
        list_row.append(text2)
    list_rows.append(list_row)

# 2次元リストをヘッダとデータに分割
header = list_rows[0]
data = list_rows[1:]

# データフレームに変換
df = pd.DataFrame(data,columns = header)

# 代替スクリプト

# 文字コードをUTF-8に変換してソース取り込み
html = driver.page_source.encode('utf-8')

# BeautifulSoupでデータ抽出
soup = BeautifulSoup(html, "html.parser")

# soupから３番目のtableを抽出
table = soup.find_all("table",attrs={"cellspacing" : "1"})[2]
rows = table.findAll("tr")

filename = "table.csv"
with open(filename, "w", encoding='utf-8') as file:
    writer = csv.writer(file)
    for row in rows:
        csvRow = []
        for cell in row.findAll(['td', 'th']):
            text = cell.get_text()
            text2 = text.replace('"','').replace("\n","").replace(" ","").replace("　","")
            csvRow.append(text2)
        writer.writerow(csvRow)

# CSVファイルをデータフレームに変換
df = pd.read_csv(filename)

# 旧スクリプト

# 文字コードをUTF-8に変換してソース取り込み
html = driver.page_source.encode('utf-8')

# BeautifulSoupでデータ抽出
soup = BeautifulSoup(html, "html.parser")

# soupから３番目のtableを抽出
table_data = soup.find_all("table",attrs={"cellspacing" : "1"})
df_stock_specific = pd.read_html(str(table_data), header=0)[2]
labels_specific = ['A','B','C','D','E']
df_stock_specific2 = df_stock_specific.reindex(labels_specific, axis=1)