def main():
args = get_input_args()
df = io_lib.df_from_input(args)
# extract parameters from arg parser
nbins = args.nbins[0]
range_tup = args.range
layout_tup = args.layout
alpha = args.alpha[0]
do_density = args.density
sharex = args.sharex
sharey = args.sharey
cols = args.cols if args.cols else [df.columns[0]]
validate_args(args, cols, df)
plot_lib.set_plot_styling(args)
# no plotting if output requested
if args.quiet:
counts, edges = np.histogram(
df[cols[0]], bins=nbins, range=range_tup, density=do_density)
centers = edges[:-1] + 0.5 * np.diff(edges)
df_out = pd.DataFrame({'bins': centers, 'counts': counts})
io_lib.df_to_output(args, df_out)
# otherwise do plotting
else:
df.hist(cols, bins=nbins, range=range_tup,
alpha=alpha, sharex=sharex, sharey=sharey, layout=layout_tup,
normed=do_density)
plot_lib.refine_plot(args)
plot_lib.show(args)
def main():
args = get_input_args()
df = io_lib.df_from_input(args)
# extract parameters from arg parser
nbins = args.nbins[0]
range_tup = args.range
layout_tup = args.layout
alpha = args.alpha[0]
do_density = args.density
sharex = args.sharex
sharey = args.sharey
cols = args.cols if args.cols else [df.columns[0]]
validate_args(args, cols, df)
plot_lib.set_plot_styling(args)
# no plotting if output requested
if args.quiet:
counts, edges = np.histogram(df[cols[0]],
bins=nbins,
range=range_tup,
density=do_density)
centers = edges[:-1] + 0.5 * np.diff(edges)
df_out = pd.DataFrame({'bins': centers, 'counts': counts})
io_lib.df_to_output(args, df_out)
# otherwise do plotting
else:
df.hist(cols,
bins=nbins,
range=range_tup,
alpha=alpha,
sharex=sharex,
sharey=sharey,
layout=layout_tup,
normed=do_density)
plot_lib.refine_plot(args)
plot_lib.show(args)
def exec_plot_command(args, cmd, df): # pragma: no cover
from pandashells.lib import plot_lib
plot_lib.set_plot_styling(args)
execute(cmd, scope_entries={'df': df})
plot_lib.refine_plot(args)
plot_lib.show(args)
def main():
msg = textwrap.dedent(
"""
Create a single variable regression plot of specified order.
-----------------------------------------------------------------------
Examples:
* Fit a line to synthetic data with boostrap errors.
p.linspace 0 10 20 \\
| p.df 'df["y_true"] = .2 * df.x' \\
'df["noise"] = np.random.randn(20)' \\
'df["y"] = df.y_true + df.noise' --names x \\
| p.regplot -x x -y y
* Fit a quadratic to synthetic data with boostrap errors.
p.linspace 0 10 40 \\
| p.df 'df["y_true"] = .5 * df.x + .3 * df.x ** 2'\\
'df["noise"] = np.random.randn(40)' \\
'df["y"] = df.y_true + df.noise' --names x \\
| p.regplot -x x -y y --order 2
* Fit sealevel data with no bootstrap
p.example_data -d sealevel\\
| p.regplot -x year -y sealevel_mm --n_boot 1
-----------------------------------------------------------------------
"""
)
# read command line arguments
parser = argparse.ArgumentParser(
formatter_class=argparse.RawDescriptionHelpFormatter, description=msg)
arg_lib.add_args(parser, 'io_in', 'io_out', 'decorating')
msg = 'Column for dependent variable'
parser.add_argument('-x', nargs=1, type=str, dest='x', metavar='col',
help=msg, required=True)
msg = 'Column for independent variable'
parser.add_argument('-y', nargs=1, type=str, dest='y',
metavar='col', help=msg, required=True)
msg = 'The order of the polynomial to fit (default = 1)'
parser.add_argument('--order', help=msg, nargs=1, default=[1], type=int)
msg = 'Number of bootstrap samples for uncertainty region (default=1000)'
parser.add_argument(
'--n_boot', help=msg, nargs=1, default=[1000], type=int)
parser.add_argument('-a', '--alpha', help='Set opacity',
nargs=1, default=[0.5], type=float)
# parse arguments
args = parser.parse_args()
# get the input dataframe
df = io_lib.df_from_input(args)
# extract command line params
x = df[args.x[0]].values
y = df[args.y[0]].values
# do a polyfit with the specified order
coeffs = np.polyfit(x, y, args.order[0])
label = make_label(coeffs, args.savefig)
sns.regplot(
x, y, order=args.order[0], n_boot=args.n_boot[0],
line_kws={'label': label, 'color': CC[2], 'alpha': .5},
scatter_kws={'alpha': args.alpha[0], 'color': CC[0]})
pl.legend(loc='best')
pl.xlabel(args.x[0])
pl.ylabel(args.y[0])
plot_lib.refine_plot(args)
plot_lib.show(args)
def main():
msg = textwrap.dedent(
"""
Plots the emperical cumulative distribution function (ECDF).
-----------------------------------------------------------------------
Examples:
* Plot ECDF for 10k samples from the standard normal distribution.
p.rand -t normal -n 10000 | p.cdf -c c0
* Instead of plotting, send ECDF values to stdout
p.rand -t normal -n 10000 | p.cdf -c c0 -q | head
-----------------------------------------------------------------------
"""
)
# read command line arguments
parser = argparse.ArgumentParser(
formatter_class=argparse.RawDescriptionHelpFormatter, description=msg)
# specify column to use
parser.add_argument(
"-c", "--col", required=True, nargs=1,
help="Column to plot distribution")
parser.add_argument(
'-n', '--n_points', nargs=1, type=int,
help='Number of output points (default is twice input len)')
parser.add_argument(
'-q', '--quiet', action='store_true', default=False,
help='Quiet mean no plots. Send numeric output to stdout instead')
# parse arguments
arg_lib.add_args(parser, 'decorating', 'io_in', 'io_out',)
args = parser.parse_args()
# get the input dataframe and extract column
df = io_lib.df_from_input(args)
x = df[args.col[0]].values
# create the output distribution
n_out = 2 * len(x) if args.n_points is None else args.n_points[0]
x_out = np.linspace(min(x), max(x), n_out)
y_out = ECDF(x)(x_out)
# send values to stdout if quiet specified
if args.quiet:
df_out = pd.DataFrame(
{'x': x_out, 'p_less': y_out, 'p_greater': 1 - y_out})
df_out = df_out[['x', 'p_less', 'p_greater']]
io_lib.df_to_output(args, df_out)
return
# set the appropriate theme ad make plot
plot_lib.set_plot_styling(args)
pl.plot(x_out, y_out, label='P({} < x)'.format(args.col[0]))
pl.plot(x_out, 1. - y_out, label='P({} > x)'.format(args.col[0]))
pl.xlabel('x')
pl.legend(loc='best')
plot_lib.refine_plot(args)
plot_lib.show(args)
def exec_plot_command(args, cmd, df): # pragma: no cover
from pandashells.lib import plot_lib
plot_lib.set_plot_styling(args)
execute(cmd, scope_entries={'df': df})
plot_lib.refine_plot(args)
plot_lib.show(args)
