def _calculate(self, data):
self._print_warning(_MSG_STATUS)
x = data.pop('x')
y = data.pop('y')
bins = self.params['bins']
drop = self.params['drop']
right = self.params['right']
weight = make_iterable_ntimes(self.params['weight'], len(x))
# create the cutting parameters
x_assignments, xbreaks = pd.cut(x,
bins=bins,
labels=False,
right=right,
retbins=True)
y_assignments, ybreaks = pd.cut(y,
bins=bins,
labels=False,
right=right,
retbins=True)
# create rectangles
# xmin, xmax, ymin, ymax, fill=count
df = pd.DataFrame({
'xbin': x_assignments,
'ybin': y_assignments,
'weights': weight
})
table = pd.pivot_table(df,
values='weights',
index=['xbin', 'ybin'],
aggfunc=np.sum)
rects = np.array([[
xbreaks[i], xbreaks[i + 1], ybreaks[j], ybreaks[j + 1],
table[(i, j)]
] for (i, j) in table.keys()])
new_data = pd.DataFrame(
rects, columns=['xmin', 'xmax', 'ymin', 'ymax', 'fill'])
# !!! assign colors???
# TODO: Remove this when visual mapping is applied after
# computing the stats
new_data['fill'] = ['#333333'] * len(new_data)
# Copy the other aesthetics into the new dataframe
# Note: There probably shouldn't be any for this stat
n = len(new_data)
for ae in data:
new_data[ae] = make_iterable_ntimes(data[ae].iloc[0], n)
return new_data
def _calculate(self, data):
x = data.pop('x')
try:
float(x.iloc[0])
except:
try:
# try to use it as a pandas.tslib.Timestamp
x = [ts.toordinal() for ts in x]
except:
raise GgplotError("stat_density(): aesthetic x mapping " +
"needs to be convertable to float!")
# TODO: Implement weight
try:
weight = data.pop('weight')
except KeyError:
weight = np.ones(len(x))
# TODO: Get "full" range of densities
# i.e tail off to zero like ggplot2? But there is nothing
# wrong with the current state.
kde = gaussian_kde(x)
bottom = np.min(x)
top = np.max(x)
step = (top - bottom) / 1000.0
x = np.arange(bottom, top, step)
y = kde.evaluate(x)
new_data = pd.DataFrame({'x': x, 'y': y})
# Copy the other aesthetics into the new dataframe
n = len(x)
for ae in data:
new_data[ae] = make_iterable_ntimes(data[ae].iloc[0], n)
return new_data
def _calculate(self, data):
x = data.pop('x')
try:
float(x.iloc[0])
except:
try:
# try to use it as a pandas.tslib.Timestamp
x = [ts.toordinal() for ts in x]
except:
raise GgplotError("stat_density(): aesthetic x mapping " +
"needs to be convertable to float!")
# TODO: Implement weight
try:
weight = data.pop('weight')
except KeyError:
weight = np.ones(len(x))
# TODO: Get "full" range of densities
# i.e tail off to zero like ggplot2? But there is nothing
# wrong with the current state.
kde = gaussian_kde(x)
bottom = np.min(x)
top = np.max(x)
step = (top - bottom) / 1000.0
x = np.arange(bottom, top, step)
y = kde.evaluate(x)
new_data = pd.DataFrame({'x': x, 'y': y})
# Copy the other aesthetics into the new dataframe
n = len(x)
for ae in data:
new_data[ae] = make_iterable_ntimes(data[ae].iloc[0], n)
return new_data
def _plot_unit(self, pinfo, ax):
slope = pinfo["slope"]
intercept = pinfo["intercept"]
n = len(slope)
linewidth = make_iterable_ntimes(pinfo["linewidth"], n)
linestyle = make_iterable_ntimes(pinfo["linestyle"], n)
alpha = make_iterable_ntimes(pinfo["alpha"], n)
color = make_iterable_ntimes(pinfo["color"], n)
ax.set_autoscale_on(False)
xlim = ax.get_xlim()
_x = np.array([np.min(xlim), np.max(xlim)])
for i in range(len(slope)):
_y = _x * slope[i] + intercept[i]
ax.plot(_x, _y, linewidth=linewidth[i], linestyle=linestyle[i], alpha=alpha[i], color=color[i])
def _calculate(self, data):
self._print_warning(_MSG_STATUS)
x = data.pop('x')
y = data.pop('y')
bins = self.params['bins']
drop = self.params['drop']
right = self.params['right']
weight = make_iterable_ntimes(self.params['weight'], len(x))
# create the cutting parameters
x_assignments, xbreaks = pd.cut(x, bins=bins, labels=False,
right=right, retbins=True)
y_assignments, ybreaks = pd.cut(y, bins=bins, labels=False,
right=right, retbins=True)
# create rectangles
# xmin, xmax, ymin, ymax, fill=count
df = pd.DataFrame({'xbin': x_assignments,
'ybin': y_assignments,
'weights': weight})
table = pd.pivot_table(df, values='weights',
index=['xbin', 'ybin'], aggfunc=np.sum)
rects = np.array([[xbreaks[i], xbreaks[i+1],
ybreaks[j], ybreaks[j+1],
table[(i, j)]]
for (i, j) in table.keys()])
new_data = pd.DataFrame(rects, columns=['xmin', 'xmax',
'ymin', 'ymax',
'fill'])
# !!! assign colors???
# TODO: Remove this when visual mapping is applied after
# computing the stats
new_data['fill'] = ['#333333'] * len(new_data)
# Copy the other aesthetics into the new dataframe
# Note: There probably shouldn't be any for this stat
n = len(new_data)
for ae in data:
new_data[ae] = make_iterable_ntimes(data[ae].iloc[0], n)
return new_data
def _plot_unit(self, pinfo, ax):
slope = pinfo['slope']
intercept = pinfo['intercept']
n = len(slope)
linewidth = make_iterable_ntimes(pinfo['linewidth'], n)
linestyle = make_iterable_ntimes(pinfo['linestyle'], n)
alpha = make_iterable_ntimes(pinfo['alpha'], n)
color = make_iterable_ntimes(pinfo['color'], n)
ax.set_autoscale_on(False)
xlim = ax.get_xlim()
_x = np.array([np.min(xlim), np.max(xlim)])
for i in range(len(slope)):
_y = _x * slope[i] + intercept[i]
ax.plot(_x, _y,
linewidth=linewidth[i],
linestyle=linestyle[i],
alpha=alpha[i],
color=color[i])
def _calculate(self, data):
x = pop(data, 'x', None)
y = pop(data, 'y', None)
# intercept and slope may be one of:
# - aesthetics to geom_abline or
# - parameter settings to stat_abline
slope = pop(data, 'slope', self.params['slope'])
intercept = pop(data, 'intercept', self.params['intercept'])
if hasattr(slope, '__call__'):
if x is None or y is None:
raise GgplotError(
'To compute the slope, x & y aesthetics are needed')
try:
slope = slope(x, y)
except TypeError as err:
raise GgplotError(*err.args)
if hasattr(intercept, '__call__'):
if x is None or y is None:
raise GgplotError(
'To compute the intercept, x & y aesthetics are needed')
try:
intercept = intercept(x, y)
except TypeError as err:
raise GgplotError(*err.args)
try:
n = len(slope)
except TypeError:
n = 1
try:
_n = len(intercept)
except TypeError:
_n = 1
if n != _n:
raise GgplotError('Specified {} slopes but {} intercepts'.format(
n, _n))
slope = make_iterable(slope)
intercept = make_iterable(intercept)
new_data = pd.DataFrame({'slope': slope, 'intercept': intercept})
# Copy the other aesthetics into the new dataframe
n = len(slope)
for ae in data:
new_data[ae] = make_iterable_ntimes(data[ae].iloc[0], n)
return new_data
def _calculate(self, data):
x = pop(data, 'x', None)
y = pop(data, 'y', None)
# intercept and slope may be one of:
# - aesthetics to geom_abline or
# - parameter settings to stat_abline
slope = pop(data, 'slope', self.params['slope'])
intercept = pop(data, 'intercept', self.params['intercept'])
if hasattr(slope, '__call__'):
if x is None or y is None:
raise GgplotError(
'To compute the slope, x & y aesthetics are needed')
try:
slope = slope(x, y)
except TypeError as err:
raise GgplotError(*err.args)
if hasattr(intercept, '__call__'):
if x is None or y is None:
raise GgplotError(
'To compute the intercept, x & y aesthetics are needed')
try:
intercept = intercept(x, y)
except TypeError as err:
raise GgplotError(*err.args)
try:
n = len(slope)
except TypeError:
n = 1
try:
_n = len(intercept)
except TypeError:
_n = 1
if n != _n:
raise GgplotError(
'Specified {} slopes but {} intercepts'.format(n, _n))
slope = make_iterable(slope)
intercept = make_iterable(intercept)
new_data = pd.DataFrame({'slope': slope, 'intercept': intercept})
# Copy the other aesthetics into the new dataframe
n = len(slope)
for ae in data:
new_data[ae] = make_iterable_ntimes(data[ae].iloc[0], n)
return new_data
def _calculate(self, data):
if self.params['fun_y'] or self.params['fun_ymin'] or self.params['fun_ymax']:
fun_data = lambda s: combined_fun_data(s, self.params['fun_y'], self.params['fun_ymin'], self.params['fun_ymax'])
elif isinstance(self.params['fun_data'], string_types):
fun_data = function_dict[self.params['fun_data']]
else:
fun_data = self.params['fun_data']
new_data = data.groupby('x').apply(lambda df: fun_data(df['y'])).reset_index()
data.pop('x')
data.pop('y')
# Copy the other aesthetics into the new dataframe
n = len(new_data.x)
for ae in data:
new_data[ae] = make_iterable_ntimes(data[ae].iloc[0], n)
return new_data
def _calculate(self, data):
x = pop(data, 'x', None)
# xintercept may be one of:
# - aesthetic to geom_vline or
# - parameter setting to stat_vline
xintercept = pop(data, 'xintercept', self.params['xintercept'])
if hasattr(xintercept, '__call__'):
if x is None:
raise GgplotError(
'To compute the intercept, x aesthetic is needed')
try:
xintercept = xintercept(x)
except TypeError as err:
raise GgplotError(*err.args)
xintercept = make_iterable(xintercept)
new_data = pd.DataFrame({'xintercept': xintercept})
# Copy the other aesthetics into the new dataframe
n = len(xintercept)
for ae in data:
new_data[ae] = make_iterable_ntimes(data[ae].iloc[0], n)
return new_data
def _calculate(self, data):
# sort data by x and
# convert x and y to lists so that the Series index
# does not mess with the smoothing functions
data = data.sort(['x'])
x = list(data.pop('x'))
y = list(data.pop('y'))
se = self.params['se']
level = self.params['level']
method = self.params['method']
span = self.params['span']
window = self.params['window']
if window is None:
window = int(np.ceil(len(x) / 10.0))
# TODO: fix the smoothers
# - lm : y1, y2 are NaNs
# - mvg: investigate unexpected looking output
if method == "lm":
x, y, y1, y2 = smoothers.lm(x, y, 1-level)
elif method == "ma":
x, y, y1, y2 = smoothers.mavg(x, y, window=window)
else:
x, y, y1, y2 = smoothers.lowess(x, y, span=span)
new_data = pd.DataFrame({'x': x, 'y': y})
if se:
new_data['ymin'] = y1
new_data['ymax'] = y2
# Copy the other aesthetics into the new dataframe
n = len(x)
for ae in data:
new_data[ae] = make_iterable_ntimes(data[ae].iloc[0], n)
return new_data
def _calculate(self, data):
# sort data by x and
# convert x and y to lists so that the Series index
# does not mess with the smoothing functions
data = data.sort(['x'])
x = list(data.pop('x'))
y = list(data.pop('y'))
se = self.params['se']
level = self.params['level']
method = self.params['method']
span = self.params['span']
window = self.params['window']
if window is None:
window = int(np.ceil(len(x) / 10.0))
# TODO: fix the smoothers
# - lm : y1, y2 are NaNs
# - mvg: investigate unexpected looking output
if method == "lm":
x, y, y1, y2 = smoothers.lm(x, y, 1 - level)
elif method == "ma":
x, y, y1, y2 = smoothers.mavg(x, y, window=window)
else:
x, y, y1, y2 = smoothers.lowess(x, y, span=span)
new_data = pd.DataFrame({'x': x, 'y': y})
if se:
new_data['ymin'] = y1
new_data['ymax'] = y2
# Copy the other aesthetics into the new dataframe
n = len(x)
for ae in data:
new_data[ae] = make_iterable_ntimes(data[ae].iloc[0], n)
return new_data
def _calculate(self, data):
x = data.pop('x')
fun = self.params['fun']
n = self.params['n']
args = self.params['args']
if not hasattr(fun, '__call__'):
raise GgplotError("stat_function requires parameter 'fun' to be " +
"a function or any other callable object")
old_fun = fun
if isinstance(args,list):
fun = lambda x: old_fun(x, *args)
elif isinstance(args,dict):
fun = lambda x: old_fun(x, **args)
elif args is not None:
fun = lambda x: old_fun(x, args)
else:
fun = lambda x: old_fun(x)
x = np.linspace(x.min(), x.max(),n)
y = list(map(fun, x))
new_data = pd.DataFrame({'x': x, 'y': y})
# Copy the other aesthetics into the new dataframe
# Don't copy the any previous 'y' assignments
try:
del data['y']
except KeyError:
pass
n = len(x)
for ae in data:
new_data[ae] = make_iterable_ntimes(data[ae].iloc[0], n)
return new_data
def _calculate(self, data):
x = data.pop('x')
right = self.params['right']
# y values are not needed
try:
del data['y']
except KeyError:
pass
else:
self._print_warning(_MSG_YVALUE)
if len(x) > 0 and isinstance(x.get(0), datetime.date):
def convert(d):
d = datetime.datetime.combine(d, datetime.datetime.min.time())
return time.mktime(d.timetuple())
x = x.apply(convert)
elif len(x) > 0 and isinstance(x.get(0), datetime.datetime):
x = x.apply(lambda d: time.mktime(d.timetuple()))
elif len(x) > 0 and isinstance(x.get(0), datetime.time):
raise GgplotError("Cannot recognise the type of x")
# If weight not mapped to, use one (no weight)
try:
weights = data.pop('weight')
except KeyError:
weights = np.ones(len(x))
else:
weights = make_iterable_ntimes(weights, len(x))
if is_categorical(x.values):
x_assignments = x
x = self.labels
width = make_iterable_ntimes(self.params['width'], self.length)
elif cbook.is_numlike(x.iloc[0]):
x_assignments = pd.cut(x, bins=self.breaks, labels=False,
right=right)
width = np.diff(self.breaks)
x = [self.breaks[i] + width[i] / 2
for i in range(len(self.breaks)-1)]
else:
raise GgplotError("Cannot recognise the type of x")
# Create a dataframe with two columns:
# - the bins to which each x is assigned
# - the weights of each x value
# Then create a weighted frequency table
_df = pd.DataFrame({'assignments': x_assignments,
'weights': weights
})
_wfreq_table = pd.pivot_table(_df, values='weights',
rows=['assignments'], aggfunc=np.sum)
# For numerical x values, empty bins get have no value
# in the computed frequency table. We need to add the zeros and
# since frequency table is a Series object, we need to keep it ordered
try:
empty_bins = set(self.labels) - set(x_assignments)
except:
empty_bins = set(range(len(width))) - set(x_assignments)
_wfreq_table = _wfreq_table.to_dict()
for _b in empty_bins:
_wfreq_table[_b] = 0
_wfreq_table = pd.Series(_wfreq_table).sort_index()
y = list(_wfreq_table)
new_data = pd.DataFrame({'x': x, 'y': y, 'width': width})
# Copy the other aesthetics into the new dataframe
n = len(x)
for ae in data:
new_data[ae] = make_iterable_ntimes(data[ae].iloc[0], n)
return new_data
def _calculate(self, data):
x = data.pop('x')
breaks = self.params['breaks']
right = self.params['right']
binwidth = self.params['binwidth']
# y values are not needed
try:
del data['y']
except KeyError:
pass
else:
self._print_warning(_MSG_YVALUE)
# If weight not mapped to, use one (no weight)
try:
weights = data.pop('weight')
except KeyError:
weights = np.ones(len(x))
else:
weights = make_iterable_ntimes(weights, len(x))
categorical = is_categorical(x.values)
if categorical:
x_assignments = x
x = sorted(set(x))
width = make_iterable_ntimes(self.params['width'], len(x))
elif cbook.is_numlike(x.iloc[0]):
if breaks is None and binwidth is None:
_bin_count = 30
self._print_warning(_MSG_BINWIDTH)
if binwidth:
_bin_count = int(np.ceil(np.ptp(x))) / binwidth
# Breaks have a higher precedence and,
# pandas accepts either the breaks or the number of bins
_bins_info = breaks or _bin_count
x_assignments, breaks = pd.cut(x, bins=_bins_info, labels=False,
right=right, retbins=True)
width = np.diff(breaks)
x = [breaks[i] + width[i] / 2
for i in range(len(breaks)-1)]
else:
raise GgplotError("Cannot recognise the type of x")
# Create a dataframe with two columns:
# - the bins to which each x is assigned
# - the weights of each x value
# Then create a weighted frequency table
_df = pd.DataFrame({'assignments': x_assignments,
'weights': weights
})
_wfreq_table = pd.pivot_table(_df, values='weights',
rows=['assignments'], aggfunc=np.sum)
# For numerical x values, empty bins get have no value
# in the computed frequency table. We need to add the zeros and
# since frequency table is a Series object, we need to keep it ordered
if len(_wfreq_table) < len(x):
empty_bins = set(range(len(x))) - set(x_assignments)
for _b in empty_bins:
_wfreq_table[_b] = 0
_wfreq_table = _wfreq_table.sort_index()
y = list(_wfreq_table)
new_data = pd.DataFrame({'x': x, 'y': y, 'width': width})
# Copy the other aesthetics into the new dataframe
n = len(x)
for ae in data:
new_data[ae] = make_iterable_ntimes(data[ae].iloc[0], n)
return new_data
