시각화하기 (Visualization)¶

pandas Dataframe 에 담긴 데이터를 그래프로 그려 봅니다.

• Seaborn 라이브러리로 이미지 형태로 그려봅니다.
• plotly 라이브러리로 반응형 그래프를 그려봅니다.

In [1]:

# 필요 라이브러리 설치
%pip install -U matplotlib seaborn plotly

# 필요 라이브러리 설치 %pip install -U matplotlib seaborn plotly

Successfully installed contourpy-1.3.1 cycler-0.12.1 fonttools-4.55.3 kiwisolver-1.4.8 matplotlib-3.10.0 pillow-11.0.0 plotly-5.24.1 pyparsing-3.2.0 seaborn-0.13.2 tenacity-9.0.0

[notice] A new release of pip is available: 24.0 -> 24.3.1
[notice] To update, run: pip install --upgrade pip
Note: you may need to restart the kernel to use updated packages.

In [1]:

import pandas as pd

df = pd.read_csv("./AAPL_data.csv")[2:]
df

import pandas as pd df = pd.read_csv("./AAPL_data.csv")[2:] df

Out[1]:

	Price	Close	High	Low	Open	Volume
2	2023-01-03	123.7684555053711	129.53777972145332	122.87781986866916	128.92423659950236	112117500
3	2023-01-04	125.04503631591797	127.32110440506466	123.77835783326215	125.56951966733021	89113600
4	2023-01-05	123.71897888183594	126.44036106917035	123.46169000194207	125.80702181866339	80962700
5	2023-01-06	128.27110290527344	128.93412872931725	123.59032994150238	124.6986773645302	87754700
6	2023-01-09	128.7955780029297	132.02166222689684	128.53828914886986	129.11225514638548	70790800
...	...	...	...	...	...	...
247	2023-12-22	192.6561737060547	194.45734722393942	192.02924020237552	194.22845757962483	37122800
248	2023-12-26	192.10885620117188	192.94475743470915	191.88992751842636	192.66612369019674	28919300
249	2023-12-27	192.20835876464844	192.5566585360189	190.15840400250286	191.55158790358445	48087700
250	2023-12-28	192.6362762451172	193.71101293849657	192.22827139973785	193.1935437488545	34049900
251	2023-12-29	191.5913848876953	193.452263485871	190.7952819760843	192.9547010641641	42628800

250 rows × 6 columns

In [17]:

df["Open"] = df["Open"].astype('float')
df["Volume"] = df["Volume"].astype('float')
df["Close"] = df["Close"].astype('float')
df['date'] = pd.to_datetime(df["Price"])
df.dtypes

df["Open"] = df["Open"].astype('float') df["Volume"] = df["Volume"].astype('float') df["Close"] = df["Close"].astype('float') df['date'] = pd.to_datetime(df["Price"]) df.dtypes

Out[17]:

Price                   object
Close                  float64
High                    object
Low                     object
Open                   float64
Volume                 float64
date            datetime64[ns]
date_numeric             int64
dtype: object

In [3]:

import seaborn as sns

sns.lineplot(df, x = "date", y = 'Close')

import seaborn as sns sns.lineplot(df, x = "date", y = 'Close')

Out[3]:

<Axes: xlabel='date', ylabel='Close'>

In [18]:

df['date_numeric'] = (df['date'] - pd.Timestamp("2023-01-01")) // pd.Timedelta('1d')
sns.regplot(x='date_numeric', y='Close', data=df)

df['date_numeric'] = (df['date'] - pd.Timestamp("2023-01-01")) // pd.Timedelta('1d') sns.regplot(x='date_numeric', y='Close', data=df)

Out[18]:

<Axes: xlabel='date_numeric', ylabel='Close'>

In [4]:

import plotly.express as px

px.line(df, x = "date", y = 'Close')

import plotly.express as px px.line(df, x = "date", y = 'Close')

In [5]:

import plotly.graph_objects as go

# Create a figure
fig = go.Figure()

# Add line plot for 'value'
fig.add_trace(go.Scatter(x=df['date'], y=df['Close'], name='Close', mode='lines', yaxis='y1'))

# Add bar plot for 'volume' on secondary y-axis
fig.add_trace(go.Bar(x=df['date'], y=df['Volume'], name='Volume', yaxis='y2', opacity=0.6))

# Update layout for dual axes
fig.update_layout(
    title='Time vs Value and Volume',
    xaxis=dict(title='Time'),
    yaxis=dict(
        title='Value',
        titlefont=dict(color='blue'),
        tickfont=dict(color='blue'),
    ),
    yaxis2=dict(
        title='Volume',
        titlefont=dict(color='orange'),
        tickfont=dict(color='orange'),
        anchor='x',
        overlaying='y',
        side='right',
    ),
    legend=dict(orientation="h", yanchor="bottom", y=1.02, xanchor="right", x=1),
    xaxis_tickformat='%Y-%m-%d %H:%M',
)

# Show the figure
fig.show()

import plotly.graph_objects as go # Create a figure fig = go.Figure() # Add line plot for 'value' fig.add_trace(go.Scatter(x=df['date'], y=df['Close'], name='Close', mode='lines', yaxis='y1')) # Add bar plot for 'volume' on secondary y-axis fig.add_trace(go.Bar(x=df['date'], y=df['Volume'], name='Volume', yaxis='y2', opacity=0.6)) # Update layout for dual axes fig.update_layout( title='Time vs Value and Volume', xaxis=dict(title='Time'), yaxis=dict( title='Value', titlefont=dict(color='blue'), tickfont=dict(color='blue'), ), yaxis2=dict( title='Volume', titlefont=dict(color='orange'), tickfont=dict(color='orange'), anchor='x', overlaying='y', side='right', ), legend=dict(orientation="h", yanchor="bottom", y=1.02, xanchor="right", x=1), xaxis_tickformat='%Y-%m-%d %H:%M', ) # Show the figure fig.show()

In [ ]: