目录

• 使用技术点:
• 使用工具:
• 导入第三方库

# 安装对应的第三方库!pip install pandas  !pip install numpy!pip install seaborn!pip install matplotlib!pip install sklearn!pip install tensorflow

#a|T + enter  notebook运行方式import pandas as pd # 数据处理import numpy as np # 科学运算import seaborn as sns # 数据可视化import matplotlib.pyplot as plt # 数据可视化import warningsimport warningswarnings.filterwarnings("ignore")

# 设置图表与 线格式plt.rcParams["figure.figsize"] = (10, 10)plt.rcParams["lines.linewidth"] = 2plt.style.use("ggplot")# 读取数据集df = pd.read_csv("./DOGE-USD.csv")df.head() # 查看前5行

df.isnull().sum() # 统计缺失值的总和(sum())Date         0Open         5High         5Low          5Close        5Adj Close    5Volume       5dtype: int64df.duplicated().sum() # 查看重复值0# 数据类型 分布基本情况df.info()<class "pandas.core.frame.DataFrame">RangeIndex: 2591 entries, 0 to 2590Data 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   float64dtypes: float64(6), object(1)memory usage: 141.8+ KB# 转换 Date的类型df["Date"] = pd.to_datetime(df.Date, dayfirst=True)# 索引重置 让Date时间格式成为 索引  inplace新建对象df.set_index("Date", inplace=True)df

df = df.asfreq("d") # 按照天数采集数据df = df.fillna(method="bfill") # 缺失值填充 下一条数据填充df

# 开盘价的分布情况df["Open"].plot(figsize=(12, 8))

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

# 投资价值df["Total Pos"] = df.sum(axis=1)df["Total Pos"].plot(figsize=(10, 8))

# 当前元素与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))

# 按照年份进行采样df.resample(rule="A").mean()

# 年平均收盘价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")

# 分别获取对应时间窗口  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)

df[["Open", "6-month-SMA", "12-month-SMA", "2-month-SMA"]].plot(figsize=(24, 10))

df[["Open","6-month-SMA"]].plot(figsize=(18,10))

df[["Open","6-month-SMA"]].iloc[:100].plot(figsize=(12,6)).autoscale(axis="x",tight=True)

df["EWMA12"] = df["Open"].ewm(span=14,adjust=True).mean()df[["Open","EWMA12"]].plot(figsize=(24,12))

df[["Open","EWMA12"]].iloc[:50].plot(figsize=(12,6)).autoscale(axis="x",tight=True)