df.isnull().sum() # 統(tǒng)計(jì)缺失值的總和(sum())
Date         0
Open         5
High         5
Low          5
Close        5
Adj Close    5
Volume       5
dtype: int64
df.duplicated().sum() # 查看重復(fù)值
0
# 數(shù)據(jù)類型 分布基本情況
df.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 2591 entries, 0 to 2590
Data columns (total 7 columns):
 #   Column     Non-Null Count  Dtype  
---  ------     --------------  -----  
 0   Date       2591 non-null   object 
 1   Open       2586 non-null   float64
 2   High       2586 non-null   float64
 3   Low        2586 non-null   float64
 4   Close      2586 non-null   float64
 5   Adj Close  2586 non-null   float64
 6   Volume     2586 non-null   float64
dtypes: float64(6), object(1)
memory usage: 141.8+ KB
# 轉(zhuǎn)換 Date的類型
df['Date'] = pd.to_datetime(df.Date, dayfirst=True)
# 索引重置 讓Date時(shí)間格式成為 索引  inplace新建對(duì)象
df.set_index('Date', inplace=True)
df

df = df.asfreq('d') # 按照天數(shù)采集數(shù)據(jù)
df = df.fillna(method='bfill') # 缺失值填充 下一條數(shù)據(jù)填充
df

# 開盤價(jià)的分布情況
df['Open'].plot(figsize=(12, 8))

# 成交情況
df['Volume'].plot(figsize=(12, 8))

# 投資價(jià)值
df['Total Pos'] = df.sum(axis=1)
df['Total Pos'].plot(figsize=(10, 8))

# 當(dāng)前元素與先前元素的相差百分比
df['Daily Reture'] = df['Total Pos'].pct_change(1)
# 日收益率的平均
df['Daily Reture'].mean()
df['Daily Reture'].plot(kind='kde')

SR = df['Daily Reture'].mean() / df['Daily Reture'].std()
all_plot = df/df.iloc[0]
all_plot.plot(figsize=(24, 16))

df.hist(bins=100, figsize=(12, 6))

# 按照年份進(jìn)行采樣
df.resample(rule='A').mean()

# 年平均收盤價(jià)
df['Open'].resample('A').mean().plot.bar(title='Yearly Mean Closing Price', color=['#b41f7d'])

# 月度
df['Open'].resample('M').mean().plot.bar(figsize=(18, 12), color='red')

# 分別獲取對(duì)應(yīng)時(shí)間窗口  6 12 2 均值
df['6-month-SMA'] = df['Open'].rolling(window=6).mean()
df['12-month-SMA'] = df['Open'].rolling(window=12).mean()
df['2-month-SMA'] = df['Open'].rolling(window=2).mean()
df.head(10)