Holoviews 挖掘相关热图和回归图的流

Question

我想为 DataFrame 制作相关热图，为每对变量制作回归图。我已经尝试阅读所有文档，但仍然很难连接两个图，因此当我点击热图时，可以显示相应的回归图。

下面是一些示例代码：

import holoviews as hv
from holoviews import opts
import seaborn as sns
import numpy as np
import pandas as pd
hv.extension('bokeh')

df = sns.load_dataset('tips')
df = df[['total_bill', 'tip', 'size']]

corr = df.corr()
heatmap = hv.HeatMap((corr.columns, corr.index, corr))\
            .opts(tools=['tap', 'hover'], height=400, width=400, toolbar='above')

m, b = np.polyfit(df.tip, df.total_bill, deg=1)
x = np.linspace(df.tip.min(), df.tip.max())
y = m*x + b

curve = hv.Curve((x, y))\
          .opts(height=400, width=400, color='red', ylim=(0, 100))
points = hv.Scatter((df.tip, df.total_bill))

hv.Layout((points * curve) + heatmap).cols(2)

Answer 1

我用你的代码调整了文档的相关部分http://holoviews.org/reference/streams/bokeh/Tap.html。也许这会消除您的困惑。

import pandas as pd
import numpy as np
import holoviews as hv
from holoviews import opts
hv.extension('bokeh', width=90)

import seaborn as sns

# Declare dataset
df = sns.load_dataset('tips')
df = df[['total_bill', 'tip', 'size']]

# Declare HeatMap
corr = df.corr()
heatmap = hv.HeatMap((corr.columns, corr.index, corr))

# Declare Tap stream with heatmap as source and initial values
posxy = hv.streams.Tap(source=heatmap, x='total_bill', y='tip')

# Define function to compute histogram based on tap location
def tap_histogram(x, y):
    m, b = np.polyfit(df[x], df[y], deg=1)
    x_data = np.linspace(df.tip.min(), df.tip.max())
    y_data = m*x_data + b
    return hv.Curve((x_data, y_data), x, y) * hv.Scatter((df[x], df[y]), x, y)


tap_dmap = hv.DynamicMap(tap_histogram, streams=[posxy])

(heatmap + tap_dmap).opts(
    opts.Scatter(height=400, width=400, color='red', ylim=(0, 100), framewise=True),
    opts.HeatMap(tools=['tap', 'hover'], height=400, width=400, toolbar='above'),
    opts.Curve(framewise=True)
)

Answer 2

我们在建模时面临的两个常见问题是共线性和非线性。共线性可以用相关热图可视化，但是用大量 variables/features 很难探索。在下面的应用中，您可以将鼠标悬停在上面查看任意两个变量之间的相关系数。当您点击时，散点图将更新为 second-degree 拟合曲线以显示两个变量之间的非线性。

在@doopler的帮助下，我稍微修改了一下代码，在此分享一下：

import numpy as np
import pandas as pd
import holoviews as hv
hv.extension('bokeh')

# generate random data
df = pd.DataFrame(data={'col_1': np.random.normal(5, 2, 100)})

df['col_2'] = df.col_1 + np.random.gamma(5, 2, 100)
df['col_3'] = df.col_1*2 + np.random.normal(0, 10, 100)
df['col_4'] = df.col_1**2 + np.random.normal(0, 10, 100)
df['col_5'] = np.sin(df.col_1)
df['col_6'] = np.cos(df.col_1)

corr = df.corr().abs()
# mask the upper triangle of the heatmap
corr.values[np.triu_indices_from(corr, 0)] = np.nan

heatmap = hv.HeatMap((corr.columns, corr.index, corr))\
            .opts(tools=['hover'],  height=400, width=400, fontsize=9,
                  toolbar='above', colorbar=False, cmap='Blues',
                  invert_yaxis=True, xrotation=90, xlabel='', ylabel='',
                  title='Correlation Coefficient Heatmap (absolute value)')

# define tap stream with heatmap as source
tap_xy = hv.streams.Tap(source=heatmap, x='col_1', y='col_4')

# calculate correlation plot based on tap
def tap_corrplot(x, y):
    # drop missing values if there are any
    df_notnull = df[[x, y]].dropna(how='any')

    # fit a 2nd degree line/curve
    m1, m2, b = np.polyfit(df_notnull[x], df_notnull[y], deg=2)
    # generate data to plot fitted line/curve
    x_curve = np.linspace(df[x].min(), df[x].max())
    y_curve = m1*x_curve**2 + m2*x_curve+ b

    curve = hv.Curve((x_curve, y_curve), x, y)\
              .opts(color='#fc4f30', framewise=True)

    scatter = hv.Scatter((df[x], df[y]), x, y)\
                .opts(height=400, width=400, fontsize=9, size=5,
                      alpha=0.2, ylim=(df[y].min(), df[y].max()),
                      color='#30a2da', framewise=True,
                      title='Correlation Plot (2nd degree fit)')

    return curve * scatter

# map tap in heatmap with correlation plot
tap_dmap = hv.DynamicMap(tap_corrplot, streams=[tap_xy])

layout = heatmap + tap_dmap
layout

如果您需要运行 Bokeh 应用程序：

from bokeh.server.server import Server

renderer = hv.renderer('bokeh')
app = renderer.app(layout)
server = Server({'/': app}, port=0)

server.start()
server.show('/')

该代码适用于 Jupyter Lab。如果您使用 Jupyter Notebook，请检查此 link.

Holoviews 挖掘相关热图和回归图的流

Holoviews tap stream of correlation heatmap and regression plot

correlation

bokeh

holoviews