def meas_plot_zscores(path,
metric_cols,
extra_cols,
composites,
size=None,
show=True):
"""Measure and plot z-scores for given columns in a data frame.
Args:
path (str): Path to data frame.
metric_cols (List[str]): Sequence of column names for which to
compute z-scores.
extra_cols (List[str]): Additional columns to included in the
output data frame.
composites (List[Enum]): Sequence of enums specifying the
combination, typically from :class:`vols.MetricCombos`.
size (List[int]): Sequence of ``width, height`` to size the figure;
defaults to None.
show (bool): True to display the image; defaults to True.
"""
# generate z-scores
df = pd.read_csv(path)
df = df_io.zscore_df(df, "Region", metric_cols, extra_cols, True)
# generate composite score column
df_comb = df_io.combine_cols(df, composites)
df_io.data_frames_to_csv(
df_comb, libmag.insert_before_ext(config.filename, "_zhomogeneity"))
# shift metrics from each condition to separate columns
conds = np.unique(df["Condition"])
df = df_io.cond_to_cols_df(df, ["Sample", "Region"], "Condition",
"original", metric_cols)
path = libmag.insert_before_ext(config.filename, "_zscore")
df_io.data_frames_to_csv(df, path)
# display as probability plot
lims = (-3, 3)
plot_2d.plot_probability(path,
conds,
metric_cols,
"Volume",
xlim=lims,
ylim=lims,
title="Region Match Z-Scores",
fig_size=size,
show=show,
suffix=None,
df=df)
def meas_plot_coefvar(path, id_cols, cond_col, cond_base, metric_cols,
composites, size_col=None, size=None, show=True):
"""Measure and plot coefficient of variation (CV) as a scatter plot.
CV is computed two ways:
- Based on columns and equation specified in ``composites``, applied
across all samples regardless of group
- For each metric in ``metric_cols``, separated by groups
Args:
path (str): Path to data frame.
id_cols (List[str]): Sequence of columns to serve as index/indices.
cond_col (str): Name of the condition column.
cond_base (str): Name of the condition to which all other conditions
will be normalized.
metric_cols (List[str]): Sequence of column names for which to
compute z-scores.
composites (List[Enum]): Sequence of enums specifying the
combination, typically from :class:`vols.MetricCombos`.
size_col (str): Name of weighting column for coefficient of
variation measurement; defaults to None.
size (List[int]): Sequence of ``width, height`` to size the figure;
defaults to None.
show (bool): True to display the image; defaults to True.
"""
# measure coefficient of variation per sample-region regardless of group
df = pd.read_csv(path)
df = df_io.combine_cols(df, composites)
df_io.data_frames_to_csv(
df, libmag.insert_before_ext(config.filename, "_coefvar"))
# measure CV within each condition and shift metrics from each
# condition to separate columns
df = df_io.coefvar_df(df, [*id_cols, cond_col], metric_cols, size_col)
conds = np.unique(df[cond_col])
df = df_io.cond_to_cols_df(df, id_cols, cond_col, cond_base, metric_cols)
path = libmag.insert_before_ext(config.filename, "_coefvartransp")
df_io.data_frames_to_csv(df, path)
# display CV measured by condition as probability plot
lims = (0, 0.7)
plot_2d.plot_probability(
path, conds, metric_cols, "Volume",
xlim=lims, ylim=lims, title="Coefficient of Variation",
fig_size=size, show=show, suffix=None, df=df)