From 9371ad787a276595daa403065c639845197d3eb4 Mon Sep 17 00:00:00 2001 From: Tuhin Sharma Date: Sat, 31 May 2025 12:35:59 +0530 Subject: [PATCH 1/3] DOC: fix ES01 for pandas.plotting.autocorrelation_plot --- pandas/plotting/_misc.py | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/pandas/plotting/_misc.py b/pandas/plotting/_misc.py index 6b2b89ee2618c..47db1a57c4b5e 100644 --- a/pandas/plotting/_misc.py +++ b/pandas/plotting/_misc.py @@ -633,6 +633,16 @@ def autocorrelation_plot(series: Series, ax: Axes | None = None, **kwargs) -> Ax """ Autocorrelation plot for time series. + This method generates an autocorrelation plot for a given time series, + which helps to identify any periodic structure or correlation within the + data across various lags. The autocorrelations are computed for increasing + lags and plotted as vertical bars. Horizontal lines at 95% and 99% confidence + intervals are shown to assist in identifying statistically significant lags. The + dashed line corresponds to the 99% confidence band, which can help detect + whether observed autocorrelations deviate significantly from what would + be expected under white noise. This plot is useful in time series analysis for + identifying potential model structures, such as autoregressive components. + Parameters ---------- series : Series From 66f09ffc0f1f199adf34aa11480c5965e2ae779b Mon Sep 17 00:00:00 2001 From: Tuhin Sharma Date: Sat, 31 May 2025 14:27:30 +0530 Subject: [PATCH 2/3] fixed plot type description in extended summary --- pandas/plotting/_misc.py | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/pandas/plotting/_misc.py b/pandas/plotting/_misc.py index 47db1a57c4b5e..857084c5e5b36 100644 --- a/pandas/plotting/_misc.py +++ b/pandas/plotting/_misc.py @@ -635,13 +635,12 @@ def autocorrelation_plot(series: Series, ax: Axes | None = None, **kwargs) -> Ax This method generates an autocorrelation plot for a given time series, which helps to identify any periodic structure or correlation within the - data across various lags. The autocorrelations are computed for increasing - lags and plotted as vertical bars. Horizontal lines at 95% and 99% confidence - intervals are shown to assist in identifying statistically significant lags. The - dashed line corresponds to the 99% confidence band, which can help detect - whether observed autocorrelations deviate significantly from what would - be expected under white noise. This plot is useful in time series analysis for - identifying potential model structures, such as autoregressive components. + data across various lags. It shows the correlation of a time series with a delayed + copy of itself as a function of delay. Autocorrelation plots are useful for + checking randomness in a data set. If the data are random, the autocorrelations + should be near zero for any and all time-lag separations. If the data are not + random, then one or more of the autocorrelations will be significantly + non-zero. Parameters ---------- From 7297d0452ec4f0338ff65f4f7faa54ae076aa9ed Mon Sep 17 00:00:00 2001 From: Tuhin Sharma Date: Sat, 31 May 2025 14:29:44 +0530 Subject: [PATCH 3/3] fixed plot type description in extended summary Co-authored-by: datapythonista --- pandas/plotting/_misc.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/pandas/plotting/_misc.py b/pandas/plotting/_misc.py index 857084c5e5b36..0f2d824f37ffc 100644 --- a/pandas/plotting/_misc.py +++ b/pandas/plotting/_misc.py @@ -635,8 +635,8 @@ def autocorrelation_plot(series: Series, ax: Axes | None = None, **kwargs) -> Ax This method generates an autocorrelation plot for a given time series, which helps to identify any periodic structure or correlation within the - data across various lags. It shows the correlation of a time series with a delayed - copy of itself as a function of delay. Autocorrelation plots are useful for + data across various lags. It shows the correlation of a time series with a + delayed copy of itself as a function of delay. Autocorrelation plots are useful for checking randomness in a data set. If the data are random, the autocorrelations should be near zero for any and all time-lag separations. If the data are not random, then one or more of the autocorrelations will be significantly