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 test_show_creates_png_file(self):
"""show() saves a png file
"""
file_name = os.path.join(self.dir_name, 'plot.png')
args = MagicMock(savefig=[file_name])
plot_lib.show(args)
self.assertTrue(os.path.isfile(file_name))
def test_show_creates_png_file(self):
"""show() saves a png file
"""
file_name = os.path.join(self.dir_name, "plot.png")
args = MagicMock(savefig=[file_name])
plot_lib.show(args)
self.assertTrue(os.path.isfile(file_name))
def test_show_creates_html_file(self):
"""show() saves a png file
"""
file_name = os.path.join(self.dir_name, 'plot.html')
args = MagicMock(savefig=[file_name])
xlabel = 'my_xlabel_string'
pl.xlabel(xlabel)
plot_lib.show(args)
with open(file_name) as f:
self.assertTrue(xlabel in f.read())
def test_show_creates_html_file(self):
"""show() saves a png file
"""
file_name = os.path.join(self.dir_name, "plot.html")
args = MagicMock(savefig=[file_name])
xlabel = "my_xlabel_string"
pl.xlabel(xlabel)
plot_lib.show(args)
with open(file_name) as f:
self.assertTrue(xlabel in f.read())
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():
msg = textwrap.dedent(
"""
Performs (multivariable) linear regression. The fitting model
is specified using the R-like, patsy syntax. Input is from stdin
and output is either fitting information or the input data
with columns added for the fit and residuals.
-----------------------------------------------------------------------
Examples:
* Fit a line to the sea-level data
p.example_data -d sealevel | p.regress -m 'sealevel_mm ~ year'
* Fit a trend plus annual cycle to sealevel data
p.example_data -d sealevel \\
| p.df 'df["sin"] = np.sin(2 * np.pi * df.year)' \\
| p.df 'df["cos"] = np.cos(2 * np.pi * df.year)' \\
| p.regress -m 'sealevel_mm ~ year + cos + sin'
* Examine residual ECDF of trend plus annual fit
p.example_data -d sealevel \\
| p.df 'df["sin"] = np.sin(2 * np.pi * df.year)' \\
| p.df 'df["cos"] = np.cos(2 * np.pi * df.year)' \\
| p.regress -m 'sealevel_mm ~ year + cos + sin' --fit \\
| p.cdf -c 'resid_' --title 'ECDF of trend + annual'
* Detrend sealevel data to more clearly reveal oscillations
p.example_data -d sealevel \\
| p.regress -m 'sealevel_mm ~ year' --fit \\
| p.plot -x year -y resid_ --ylabel 'Trend removed (mm)' \\
--title 'Global Sea Surface Height'
* Set origin of sealevel data to 0 and regress with no intercept
p.example_data -d sealevel\\
| p.df 'df["year"] = df.year - df.year.iloc[0]'\\
'df["sealevel_mm"] = df.sealevel_mm - df.sealevel_mm.iloc[0]'\\
| p.regress -m 'sealevel_mm ~ year - 1' --fit\\
| p.plot -x year -y sealevel_mm fit_ --style '.' '-'\\
--alpha .2 1 --legend best --title 'Force Zero Intercept'
-----------------------------------------------------------------------
"""
)
# read command line arguments
parser = argparse.ArgumentParser(
formatter_class=argparse.RawDescriptionHelpFormatter, description=msg)
arg_lib.add_args(parser, 'io_in', 'io_out', 'example')
# specify columns to histogram
parser.add_argument("-m", "--model", type=str, nargs=1, required=True,
help="The model expressed in patsy syntax")
msg = "Return input with fit and residual appended"
parser.add_argument("--fit", action="store_true", dest='retfit',
default=False, help=msg)
parser.add_argument("--plot", action="store_true",
default=False, help="Make residual plots")
# parse arguments
args = parser.parse_args()
# get the input dataframe
df = io_lib.df_from_input(args)
# fit the model and add fit, resid columns
result = sm.ols(formula=args.model[0], data=df).fit()
df['fit_'] = result.fittedvalues
df['resid_'] = result.resid
# add and output the fit results if requested
if args.retfit:
io_lib.df_to_output(args, df)
return
# print the fit summary
sys.stdout.write('\n{}\n'.format(result.summary()))
sys.stdout.flush()
# do plots if requested
if args.plot:
pl.subplot(211)
pl.plot(df.fit_, df.resid_, '.', alpha=.5)
pl.xlabel('Fit')
pl.ylabel('Residual')
pl.title(args.model[0])
pl.subplot(212)
sns.distplot(df.resid_, bins=50)
pl.xlabel('Residual with R^2 = {:0.4f}'.format(result.rsquared))
pl.ylabel('Counts')
# annoying issue with osx backend forces if statement here
if mpl.get_backend().lower() in ['agg', 'macosx']:
pl.gcf().set_tight_layout(True)
else:
pl.gcf().tight_layout()
plot_lib.show(args)
def main():
msg = textwrap.dedent("""
Creates faceted plots using seaborn FacetGrid.
With this tool, you can create a group of plots which show aspects
of the same dataset broken down in different ways. See the seaborn
FacetGrid documentation for more detail.
The --map argument to this function specifies a function to use
for generating each of the plots. The following modules are available
in the namespace:
pl = pylab
sns = seaborn
-----------------------------------------------------------------------
Examples:
* Scatterplot of tips vs bill for different combinations of sex,
smoker, and day of the week:
p.example_data -d tips | \\
p.facet_grid --row smoker --col sex --hue day \\
--map pl.scatter \\
--args total_bill tip --kwargs 'alpha=.2' 's=100'
* Histogram of tips broken down by sex, smoker and day
p.example_data -d tips | p.facet_grid --col day \\
--row sex --hue smoker --sharex --sharey --aspect 1 \\
--map pl.hist --args tip \\
--kwargs 'alpha=.2' 'range=[0, 10]' 'bins=20'
-----------------------------------------------------------------------
""")
# read command line arguments
parser = argparse.ArgumentParser(
formatter_class=argparse.RawDescriptionHelpFormatter, description=msg)
arg_lib.add_args(parser, 'io_in')
msg = 'Different values of this variable in separate rows'
parser.add_argument('--row',
nargs=1,
type=str,
dest='row',
metavar='row',
help=msg)
msg = 'Different values of this variable in separate columns'
parser.add_argument('--col',
nargs=1,
type=str,
dest='col',
metavar='col',
help=msg)
msg = 'Different values of this variable in separate colors'
parser.add_argument('--hue',
nargs=1,
type=str,
dest='hue',
metavar='hue',
help=msg)
msg = 'The aspect ratio of each plot'
parser.add_argument('--aspect',
nargs=1,
type=float,
dest='aspect',
metavar='aspect',
default=[2],
help=msg)
msg = 'The size of each plot (default=4)'
parser.add_argument('--size',
nargs=1,
type=float,
dest='size',
metavar='size',
help=msg,
default=[4])
msg = 'The plotting function to use for each facet'
parser.add_argument('--map',
nargs=1,
type=str,
dest='map',
metavar='map',
required=True,
help=msg)
msg = 'The args to pass to the plotting function'
parser.add_argument('--args',
nargs='+',
type=str,
dest='args',
metavar='args',
required=True,
help=msg)
msg = 'Plotting function kwargs expressed as \'a=1\' \'b=2\' ... '
parser.add_argument('--kwargs',
nargs='+',
type=str,
dest='kwargs',
metavar='kwargs',
help=msg)
msg = 'Share x axis'
parser.add_argument('--sharex',
action='store_true',
dest='sharex',
default=False,
help=msg)
msg = 'Share y axis'
parser.add_argument('--sharey',
action='store_true',
dest='sharey',
default=False,
help=msg)
msg = 'x axis limits when sharex=True'
parser.add_argument('--xlim',
nargs=2,
type=float,
dest='xlim',
metavar='xlim',
help=msg)
msg = 'y axis limits when sharex=True'
parser.add_argument('--ylim',
nargs=2,
type=float,
dest='ylim',
metavar='ylim',
help=msg)
msg = "Save the figure to this file"
parser.add_argument('--savefig', nargs=1, type=str, help=msg)
warnings.filterwarnings('ignore')
# parse arguments
args = parser.parse_args()
# get the input dataframe
df = io_lib.df_from_input(args)
facet_grid_kwargs = {
'row': args.row[0] if args.row else None,
'col': args.col[0] if args.col else None,
'hue': args.hue[0] if args.hue else None,
'aspect': args.aspect[0],
'size': args.size[0],
'sharex': args.sharex,
'sharey': args.sharey,
'xlim': args.xlim if args.xlim else None,
'ylim': args.ylim if args.ylim else None,
}
grid = sns.FacetGrid(df, **facet_grid_kwargs)
map_func_name = args.map[0]
scope = {'pl': pl, 'sns': sns, 'map_func_name': map_func_name}
exec('map_func = {}'.format(map_func_name), scope)
map_func = scope['map_func']
map_args = args.args
map_kwargs = {}
if args.kwargs:
for kwarg in args.kwargs:
exec('map_kwargs.update(dict({}))'.format(kwarg))
grid.map(map_func, *map_args, **map_kwargs) # noqa defined in exec above
grid.add_legend()
plot_lib.show(args)
def test_show_calls_pylab_show(self, show_mock):
"""show() call pylab.show()
"""
args = MagicMock(savefig=[])
plot_lib.show(args)
self.assertTrue(show_mock.called)
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 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 main():
msg = textwrap.dedent(
"""
Creates faceted plots using seaborn FacetGrid.
With this tool, you can create a group of plots which show aspects
of the same dataset broken down in different ways. See the seaborn
FacetGrid documentation for more detail.
The --map argument to this function specifies a function to use
for generating each of the plots. The following modules are available
in the namespace:
pl = pylab
sns = seaborn
-----------------------------------------------------------------------
Examples:
* Scatterplot of tips vs bill for different combinations of sex,
smoker, and day of the week:
p.example_data -d tips | \\
p.facet_grid --row smoker --col sex --hue day \\
--map pl.scatter \\
--args total_bill tip --kwargs 'alpha=.2' 's=100'
* Histogram of tips broken down by sex, smoker and day
p.example_data -d tips | p.facet_grid --col day \\
--row sex --hue smoker --sharex --sharey --aspect 1 \\
--map pl.hist --args tip \\
--kwargs 'alpha=.2' 'range=[0, 10]' 'bins=20'
-----------------------------------------------------------------------
"""
)
# read command line arguments
parser = argparse.ArgumentParser(
formatter_class=argparse.RawDescriptionHelpFormatter, description=msg)
arg_lib.add_args(parser, 'io_in')
msg = 'Different values of this variable in separate rows'
parser.add_argument(
'--row', nargs=1, type=str, dest='row', metavar='row', help=msg)
msg = 'Different values of this variable in separate columns'
parser.add_argument(
'--col', nargs=1, type=str, dest='col', metavar='col', help=msg)
msg = 'Different values of this variable in separate colors'
parser.add_argument(
'--hue', nargs=1, type=str, dest='hue', metavar='hue', help=msg)
msg = 'The aspect ratio of each plot'
parser.add_argument(
'--aspect', nargs=1, type=float, dest='aspect', metavar='aspect',
default=[2], help=msg)
msg = 'The size of each plot (default=4)'
parser.add_argument(
'--size', nargs=1, type=float, dest='size', metavar='size',
help=msg, default=[4])
msg = 'The plotting function to use for each facet'
parser.add_argument(
'--map', nargs=1, type=str, dest='map', metavar='map', required=True,
help=msg)
msg = 'The args to pass to the plotting function'
parser.add_argument(
'--args', nargs='+', type=str, dest='args', metavar='args',
required=True, help=msg)
msg = 'Plotting function kwargs expressed as \'a=1\' \'b=2\' ... '
parser.add_argument(
'--kwargs', nargs='+', type=str, dest='kwargs',
metavar='kwargs', help=msg)
msg = 'Share x axis'
parser.add_argument('--sharex', action='store_true', dest='sharex',
default=False, help=msg)
msg = 'Share y axis'
parser.add_argument('--sharey', action='store_true', dest='sharey',
default=False, help=msg)
msg = 'x axis limits when sharex=True'
parser.add_argument(
'--xlim', nargs=2, type=float, dest='xlim', metavar='xlim', help=msg)
msg = 'y axis limits when sharex=True'
parser.add_argument(
'--ylim', nargs=2, type=float, dest='ylim', metavar='ylim', help=msg)
msg = "Save the figure to this file"
parser.add_argument('--savefig', nargs=1, type=str, help=msg)
warnings.filterwarnings('ignore')
# parse arguments
args = parser.parse_args()
# get the input dataframe
df = io_lib.df_from_input(args)
facet_grid_kwargs = {
'row': args.row[0] if args.row else None,
'col': args.col[0] if args.col else None,
'hue': args.hue[0] if args.hue else None,
'aspect': args.aspect[0],
'size': args.size[0],
'sharex': args.sharex,
'sharey': args.sharey,
'xlim': args.xlim if args.xlim else None,
'ylim': args.ylim if args.ylim else None,
}
grid = sns.FacetGrid(df, **facet_grid_kwargs)
map_func_name = args.map[0]
scope = {'pl': pl, 'sns': sns, 'map_func_name': map_func_name}
exec('map_func = {}'.format(map_func_name), scope)
map_func = scope['map_func']
map_args = args.args
map_kwargs = {}
if args.kwargs:
for kwarg in args.kwargs:
exec('map_kwargs.update(dict({}))'.format(kwarg))
grid.map(map_func, *map_args, **map_kwargs) # noqa defined in exec above
grid.add_legend()
plot_lib.show(args)
def main():
msg = textwrap.dedent(
"""
Creates faceted plots using seaborn FacetGrid.
With this tool, you can create a group of plots which show aspects
of the same dataset broken down in different ways. See the seaborn
FacetGrid documentation for more detail.
The --map argument to this function specifies a function to use
for generating each of the plots. The following modules are available
in the namespace:
pl = pylab
sns = seaborn
-----------------------------------------------------------------------
Examples:
* Scatterplot of tips vs bill for different combinations of sex,
smoker, and day of the week:
p.example_data -d tips | \\
p.facet_grid --row smoker --col sex --hue day \\
--map pl.scatter \\
--args total_bill tip --kwargs 'alpha=.2' 's=100'
* Histogram of tips broken down by sex, smoker and day
p.example_data -d tips | p.facet_grid --col day \\
--row sex --hue smoker --sharex --sharey --aspect 1 \\
--map pl.hist --args tip \\
--kwargs 'alpha=.2' 'range=[0, 10]' 'bins=20'
-----------------------------------------------------------------------
"""
)
# read command line arguments
parser = argparse.ArgumentParser(formatter_class=argparse.RawDescriptionHelpFormatter, description=msg)
arg_lib.add_args(parser, "io_in")
msg = "Different values of this variable in separate rows"
parser.add_argument("--row", nargs=1, type=str, dest="row", metavar="row", help=msg)
msg = "Different values of this variable in separate columns"
parser.add_argument("--col", nargs=1, type=str, dest="col", metavar="col", help=msg)
msg = "Different values of this variable in separate colors"
parser.add_argument("--hue", nargs=1, type=str, dest="hue", metavar="hue", help=msg)
msg = "The aspect ratio of each plot"
parser.add_argument("--aspect", nargs=1, type=float, dest="aspect", metavar="aspect", default=[2], help=msg)
msg = "The size of each plot (default=4)"
parser.add_argument("--size", nargs=1, type=float, dest="size", metavar="size", help=msg, default=[4])
msg = "The plotting function to use for each facet"
parser.add_argument("--map", nargs=1, type=str, dest="map", metavar="map", required=True, help=msg)
msg = "The args to pass to the plotting function"
parser.add_argument("--args", nargs="+", type=str, dest="args", metavar="args", required=True, help=msg)
msg = "Plotting function kwargs expressed as 'a=1' 'b=2' ... "
parser.add_argument("--kwargs", nargs="+", type=str, dest="kwargs", metavar="kwargs", help=msg)
msg = "Share x axis"
parser.add_argument("--sharex", action="store_true", dest="sharex", default=False, help=msg)
msg = "Share y axis"
parser.add_argument("--sharey", action="store_true", dest="sharey", default=False, help=msg)
msg = "x axis limits when sharex=True"
parser.add_argument("--xlim", nargs=2, type=float, dest="xlim", metavar="xlim", help=msg)
msg = "y axis limits when sharex=True"
parser.add_argument("--ylim", nargs=2, type=float, dest="ylim", metavar="ylim", help=msg)
msg = "Save the figure to this file"
parser.add_argument("--savefig", nargs=1, type=str, help=msg)
# parse arguments
args = parser.parse_args()
# get the input dataframe
df = io_lib.df_from_input(args)
facet_grid_kwargs = {
"row": args.row[0] if args.row else None,
"col": args.col[0] if args.col else None,
"hue": args.hue[0] if args.hue else None,
"aspect": args.aspect[0],
"size": args.size[0],
"sharex": args.sharex,
"sharey": args.sharey,
"xlim": args.xlim if args.xlim else None,
"ylim": args.ylim if args.ylim else None,
}
grid = sns.FacetGrid(df, **facet_grid_kwargs)
map_func_name = args.map[0]
scope = {"pl": pl, "sns": sns, "map_func_name": map_func_name}
exec("map_func = {}".format(map_func_name), scope)
map_func = scope["map_func"]
map_args = args.args
map_kwargs = {}
if args.kwargs:
for kwarg in args.kwargs:
exec("map_kwargs.update(dict({}))".format(kwarg))
grid.map(map_func, *map_args, **map_kwargs) # noqa defined in exec above
grid.add_legend()
plot_lib.show(args)
def main():
msg = textwrap.dedent("""
Performs (multivariable) linear regression. The fitting model
is specified using the R-like, patsy syntax. Input is from stdin
and output is either fitting information or the input data
with columns added for the fit and residuals.
-----------------------------------------------------------------------
Examples:
* Fit a line to the sea-level data
p.example_data -d sealevel | p.regress -m 'sealevel_mm ~ year'
* Fit a trend plus annual cycle to sealevel data
p.example_data -d sealevel \\
| p.df 'df["sin"] = np.sin(2 * np.pi * df.year)' \\
| p.df 'df["cos"] = np.cos(2 * np.pi * df.year)' \\
| p.regress -m 'sealevel_mm ~ year + cos + sin'
* Examine residual ECDF of trend plus annual fit
p.example_data -d sealevel \\
| p.df 'df["sin"] = np.sin(2 * np.pi * df.year)' \\
| p.df 'df["cos"] = np.cos(2 * np.pi * df.year)' \\
| p.regress -m 'sealevel_mm ~ year + cos + sin' --fit \\
| p.cdf -c 'resid_' --title 'ECDF of trend + annual'
* Detrend sealevel data to more clearly reveal oscillations
p.example_data -d sealevel \\
| p.regress -m 'sealevel_mm ~ year' --fit \\
| p.plot -x year -y resid_ --ylabel 'Trend removed (mm)' \\
--title 'Global Sea Surface Height'
* Set origin of sealevel data to 0 and regress with no intercept
p.example_data -d sealevel\\
| p.df 'df["year"] = df.year - df.year.iloc[0]'\\
'df["sealevel_mm"] = df.sealevel_mm - df.sealevel_mm.iloc[0]'\\
| p.regress -m 'sealevel_mm ~ year - 1' --fit\\
| p.plot -x year -y sealevel_mm fit_ --style '.' '-'\\
--alpha .2 1 --legend best --title 'Force Zero Intercept'
-----------------------------------------------------------------------
""")
# read command line arguments
parser = argparse.ArgumentParser(
formatter_class=argparse.RawDescriptionHelpFormatter, description=msg)
arg_lib.add_args(parser, 'io_in', 'io_out', 'example')
# specify columns to histogram
parser.add_argument("-m",
"--model",
type=str,
nargs=1,
required=True,
help="The model expressed in patsy syntax")
msg = "Return input with fit and residual appended"
parser.add_argument("--fit",
action="store_true",
dest='retfit',
default=False,
help=msg)
parser.add_argument("--plot",
action="store_true",
default=False,
help="Make residual plots")
# parse arguments
args = parser.parse_args()
# get the input dataframe
df = io_lib.df_from_input(args)
# fit the model and add fit, resid columns
result = sm.ols(formula=args.model[0], data=df).fit()
df['fit_'] = result.fittedvalues
df['resid_'] = result.resid
# add and output the fit results if requested
if args.retfit:
io_lib.df_to_output(args, df)
return
# print the fit summary
sys.stdout.write('\n{}\n'.format(result.summary()))
sys.stdout.flush()
# do plots if requested
if args.plot:
pl.subplot(211)
pl.plot(df.fit_, df.resid_, '.', alpha=.5)
pl.xlabel('Fit')
pl.ylabel('Residual')
pl.title(args.model[0])
pl.subplot(212)
sns.distplot(df.resid_, bins=50)
pl.xlabel('Residual with R^2 = {:0.4f}'.format(result.rsquared))
pl.ylabel('Counts')
# annoying issue with osx backend forces if statement here
if mpl.get_backend().lower() in ['agg', 'macosx']:
pl.gcf().set_tight_layout(True)
else:
pl.gcf().tight_layout()
plot_lib.show(args)
def test_show_calls_pylab_show(self, show_mock):
"""show() call pylab.show()
"""
args = MagicMock(savefig=[])
plot_lib.show(args)
self.assertTrue(show_mock.called)
