python - 如何更改时间序列的条形大小

Question

我正在努力对一段时间内英雄联盟玩家的游戏进行一些分析。我正在尝试使用plotly 创建直方图，日期范围在x 轴上，而没有。 y 上的游戏数量。这可行，但我无法获得每天的单独条形图，只能获得一个月的条形图。我尝试过使用 xaxis，'size' 对象，但这不会改变任何东西，我猜是因为 x 轴是日期形式。

那么问题来了，在 Plotly 中如何将直方图上的条形大小从每月 bin 大小更改为每日 bin 大小？

下面是代码示例:

from datetime import date, timedelta
import random
import plotly.plotly as py
import plotly.graph_objs as go
import numpy as np
from plotly import tools
from plotly.offline import *#plotly.offline.iplot()
init_notebook_mode(connected=True)
############## create date ranges #################

d1 = date(2014, 3, 22)  # start date
d2 = date(2014, 6, 22)  # end date

delta = d2 - d1         # timedelta
dates = []
for i in range(delta.days + 1):
    dates.append((d1 + timedelta(days=i)))


#################################################


def games_p_day():
    sizeo = 1
    trace_total = go.Histogram(
        y=[random.randint(1, 10) for y in range(1, 100)],
        x=dates,
        name = 'total games',
        xbins=dict(
        size=sizeo
    )
        )
    trace_wins = go.Histogram(
        y=[random.randint(1, 10) for y in range(1, 100)],
        x=dates,
        name = 'won games',
        xbins=dict(
            size=sizeo
    )
        )
    trace_losses = go.Histogram(
        y=[random.randint(1, 10) for y in range(1, 100)],
        x=dates,
        name = 'lost games',
        xbins=dict(
        size=sizeo
    )
        )
    layout = dict(
        title = "Wins and losses over time",
        xaxis=dict(
            rangeselector=dict(
                buttons=list([
                    dict(count=1,
                         label='1m',
                         step='month',
                         stepmode='backward'),
                    dict(count=6,
                         label='6m',
                         step='month',
                         stepmode='backward'),
                    dict(step='all')
                ])
            ),
            rangeslider=dict(),
            type='date',

        ),
        bargap=0.2,
        bargroupgap=0.1)
    data=[trace_total]
    fig = go.Figure(data=data, layout=layout)
    iplot(fig, filename = "Wins and losses over time")    

games_p_day()

非常感谢任何帮助。哦，如果您看到任何其他可以帮助我的内容(即错误的代码结构)，请告诉我!

Answer 1

直方图是 representation of the distribution的数值数据。在我看来，您的目标是对每日数据到每周数据进行聚合。也就是说，只要您希望在 x 轴上具有时间维度而不是计数、平均值或任何其他聚合函数。如果是这种情况，那么您面临的挑战的关键不在于绘图本身，而在于聚合和时间函数，例如 resample('W-Mon', on='index').sum()。以下是一些示例:

采样原始数据图:

原始数据代码:

import pandas as pd
import numpy as np
import datetime

# data
np.random.seed(12)
numdays=100
dates = pd.date_range('1/1/2020', periods=numdays)
games = np.random.randint(low=100, high=200, size=numdays).tolist()
losses = np.random.randint(low=0, high=100, size=numdays).tolist()
wins = list(np.array(games)-np.array(wins))
df = pd.DataFrame({'games': games,
                        'wins':wins,
                        'losses':losses}, index=dates)

# resample daily data to weekly sums
df2=df.reset_index().resample('W-Mon', on='index').sum()
df2['formatted_date'] = pd.to_datetime(df3.index)
df2['year'] = df2.formatted_date.apply(lambda x: x.year)
df2['week_of_year'] = df2.formatted_date.apply(lambda x: x.weekofyear)
df2['year_week'] = df2['year'].map(str)+'_'+df3['week_of_year'].map(str)

# build and show plotly plot for daily games
fig = go.Figure(data=[go.Bar(name='games', x=df.index, y=df['games'])])
fig.show()

每周汇总数据图。日期作为索引:

每周汇总数据的代码。日期作为索引:

# build and show plotly plot for weekly games. Dates as index
fig = go.Figure(data=[go.Bar(name='games', x=df2.index, y=df2['games'])])
fig.show()

每周汇总数据图。作为索引的年份和周数:

每周汇总数据的代码。作为索引的年份和周数:

# build and show plotly plot for weekly games. Year and week number as index
fig = go.Figure(data=[go.Bar(name='games', x=df2['year_week'], y=df2['games'])])
fig.show()

每周汇总数据图，按胜负划分:

每周汇总数据的代码，按胜负划分:

import pandas as pd
import numpy as np
import datetime

# data
np.random.seed(12)
numdays=100
dates = pd.date_range('1/1/2020', periods=numdays)
games = np.random.randint(low=100, high=200, size=numdays).tolist()
losses = np.random.randint(low=0, high=100, size=numdays).tolist()
wins = list(np.array(games)-np.array(wins))
df = pd.DataFrame({'games': games,
                        'wins':wins,
                        'losses':losses}, index=dates)

# resample daily data to weekly sums
df2=df.reset_index().resample('W-Mon', on='index').sum()
df2['formatted_date'] = pd.to_datetime(df3.index)
df2['year'] = df2.formatted_date.apply(lambda x: x.year)
df2['week_of_year'] = df2.formatted_date.apply(lambda x: x.weekofyear)
df2['year_week'] = df2['year'].map(str)+'_'+df3['week_of_year'].map(str)

fig = go.Figure(data=[go.Bar(name='victory', x=df2['year_week'], y=df2['wins']),
                      go.Bar(name='defeat', x=df2['year_week'], y=df2['losses'])])



fig.update_layout(barmode='group')
fig.show()