def interroplot(path, query):
import corpkit
"""Interrogates path with Tregex query, gets relative frequencies, and plots the top seven results"""
from corpkit import interrogator, editor, plotter
quickstart = interrogator(path, 'words', query)
edited = editor(quickstart.results, '%', quickstart.totals, print_info = False)
plotter(str(path), edited.results)
def interroplot(path, query):
"""Demo function for interrogator/plotter.
1. Interrogates path with Tregex query,
2. Gets relative frequencies
3. Plots the top seven results
:param path: path to corpus
:type path: str
:param query: Tregex query
:type query: str
"""
import corpkit
from corpkit import interrogator, editor, plotter
quickstart = interrogator(path, 'words', query, show = ['w'])
edited = editor(quickstart.results, '%', quickstart.totals, print_info = False)
plotter(str(path), edited.results)
# If you want to see the query and options that created the results, you can use:
# <codecell>
print allwords.query
# <markdowncell>
# ### Plotting results
# <markdowncell>
# Lists of years and totals are pretty dry. Luckily, we can use the `plotter()` function to visualise our results. At minimum, `plotter()` needs two arguments:
# 1. a title (in quotation marks)
# 2. a list of results to plot
# <codecell>
plotter('Word counts in each subcorpus', allwords.totals)
# <markdowncell>
# Because we have smaller samples for 1963 and 2014, we might want to project them. To do that, we can pass subcorpus names and projection values to `editor()`:
# <codecell>
proj_vals = [(1963, 5), (2014, 1.37)]
projected = editor(allwords.totals, projection = proj_vals)
plotter('Word counts in each subcorpus (projected)', projected.totals)
# <markdowncell>
# Great! So, we can see that the number of words per year varies quite a lot, even after projection. That's worth keeping in mind.
# <markdowncell>
# ### Frequency of risk words in the NYT
def plot(self, title, *args, **kwargs):
"""calls corpkit.plotter.plotter()"""
from corpkit import plotter
plotter(title, self, *args, **kwargs)
def plot(title,
x_label = None,
y_label = None,
style = 'ggplot',
figsize = (8, 4),
save = False,
legend_pos = 'best',
reverse_legend = 'guess',
num_to_plot = 7,
tex = 'try',
colours = 'Accent',
cumulative = False,
pie_legend = True,
partial_pie = False,
show_totals = False,
transparent = False,
output_format = 'png',
interactive = False,
black_and_white = False,
show_p_val = False,
indices = False,
**kwargs):
"""Visualise corpus interrogations.
>>> data.plot('An example plot', kind = 'bar', save = True)
:param title: A title for the plot
:type title: str
:param x_label: A label for the x axis
:type x_label: str
:param y_label: A label for the y axis
:type y_label: str
:param kind: The kind of chart to make
:type kind: str ('line'/'bar'/'barh'/'pie'/'area')
:param style: Visual theme of plot
:type style: str ('ggplot'/'bmh'/'fivethirtyeight'/'seaborn-talk'/etc)
:param figsize: Size of plot
:type figsize: tuple (int, int)
:param save: If bool, save with *title* as name; if str, use str as name
:type save: bool/str
:param legend_pos: Where to place legend
:type legend_pos: str ('upper right'/'outside right'/etc)
:param reverse_legend: Reverse the order of the legend
:type reverse_legend: bool
:param num_to_plot: How many columns to plot
:type num_to_plot: int/'all'
:param tex: Use TeX to draw plot text
:type tex: bool
:param colours: Colourmap for lines/bars/slices
:type colours: str
:param cumulative: Plot values cumulatively
:type cumulative: bool
:param pie_legend: Show a legend for pie chart
:type pie_legend: bool
:param partial_pie: Allow plotting of pie slices only
:type partial_pie: bool
:param show_totals: Print sums in plot where possible
:type show_totals: str -- 'legend'/'plot'/'both'
:param transparent: Transparent .png background
:type transparent: bool
:param output_format: File format for saved image
:type output_format: str -- 'png'/'pdf'
:param black_and_white: Create black and white line styles
:type black_and_white: bool
:param show_p_val: Attempt to print p values in legend if contained in df
:type show_p_val: bool
:param indices: To use when plotting "distance from root"
:type indices: bool
:param stacked: When making bar chart, stack bars on top of one another
:type stacked: str
:param filled: For area and bar charts, make every column sum to 100
:type filled: str
:param legend: Show a legend
:type legend: bool
:param rot: Rotate x axis ticks by *rot* degrees
:type rot: int
:param subplots: Plot each column separately
:type subplots: bool
:param layout: Grid shape to use when *subplots* is True
:type layout: tuple -- (int, int)
:param interactive: Experimental interactive options
:type interactive: list -- [1, 2, 3]
:returns: matplotlib figure
"""
from corpkit import plotter
branch = kwargs.pop('branch', 'results')
if branch.lower().startswith('r'):
plotter(title, self.results, *args, **kwargs)
elif branch.lower().startswith('t'):
plotter(title, self.totals, *args, **kwargs)
