def plot_overwrites_matrix(args, repo, people, matrix):
if args.output and args.output.endswith(".json"):
data = locals().copy()
del data["args"]
data["type"] = "overwrites_matrix"
if args.mode == "all":
output = get_plot_path(args.output, "matrix")
else:
output = args.output
with open(output, "w") as fout:
json.dump(data, fout, sort_keys=True, default=default_json)
return
matplotlib, pyplot = import_pyplot(args.backend, args.style)
s = 4 + matrix.shape[1] * 0.3
fig = pyplot.figure(figsize=(s, s))
ax = fig.add_subplot(111)
ax.xaxis.set_label_position("top")
ax.matshow(matrix, cmap=pyplot.cm.OrRd)
ax.set_xticks(numpy.arange(0, matrix.shape[1]))
ax.set_yticks(numpy.arange(0, matrix.shape[0]))
ax.set_yticklabels(people, va="center")
ax.set_xticks(numpy.arange(0.5, matrix.shape[1] + 0.5), minor=True)
ax.set_xticklabels(
["Unidentified"] + people,
rotation=45,
ha="left",
va="bottom",
rotation_mode="anchor",
)
ax.set_yticks(numpy.arange(0.5, matrix.shape[0] + 0.5), minor=True)
ax.grid(False)
ax.grid(which="minor")
apply_plot_style(fig, ax, None, args.background, args.font_size, args.size)
if not args.output:
pos1 = ax.get_position()
pos2 = (pos1.x0 + 0.15, pos1.y0 - 0.1, pos1.width * 0.9,
pos1.height * 0.9)
ax.set_position(pos2)
if args.mode == "all" and args.output:
output = get_plot_path(args.output, "matrix")
else:
output = args.output
title = "%s %d developers overwrite" % (repo, matrix.shape[0])
if args.output:
# FIXME(vmarkovtsev): otherwise the title is screwed in savefig()
title = ""
deploy_plot(title, output, args.background)
def show_devs_parallel(args, name, start_date, end_date, devs):
matplotlib, pyplot = import_pyplot(args.backend, args.style)
from matplotlib.collections import LineCollection
def solve_equations(x1, y1, x2, y2):
xcube = (x1 - x2)**3
a = 2 * (y2 - y1) / xcube
b = 3 * (y1 - y2) * (x1 + x2) / xcube
c = 6 * (y2 - y1) * x1 * x2 / xcube
d = y1 - a * x1**3 - b * x1**2 - c * x1
return a, b, c, d
# biggest = {k: max(getattr(d, k) for d in devs.values())
# for k in ("commits", "lines", "ownership")}
for k, dev in devs.items():
points = numpy.array(
[
(1, dev.commits_rank),
(2, dev.lines_rank),
(3, dev.ownership_rank),
(4, dev.couples_index),
(5, dev.commit_coocc_index),
],
dtype=float,
)
points[:, 1] = points[:, 1] / len(devs)
splines = []
for i in range(len(points) - 1):
a, b, c, d = solve_equations(*points[i], *points[i + 1])
x = numpy.linspace(i + 1, i + 2, 100)
smooth_points = numpy.array([x, a * x**3 + b * x**2 + c * x + d
]).T.reshape(-1, 1, 2)
splines.append(smooth_points)
points = numpy.concatenate(splines)
segments = numpy.concatenate([points[:-1], points[1:]], axis=1)
lc = LineCollection(segments)
lc.set_array(numpy.linspace(0, 0.1, segments.shape[0]))
pyplot.gca().add_collection(lc)
pyplot.xlim(0, 6)
pyplot.ylim(-0.1, 1.1)
deploy_plot("Developers", args.output, args.background)
def show_old_vs_new(
args: Namespace,
name: str,
start_date: int,
end_date: int,
people: List[str],
days: Dict[int, Dict[int, DevDay]],
) -> None:
from scipy.signal import convolve, slepian
start_date = datetime.fromtimestamp(start_date)
start_date = datetime(start_date.year, start_date.month, start_date.day)
end_date = datetime.fromtimestamp(end_date)
end_date = datetime(end_date.year, end_date.month, end_date.day)
new_lines = numpy.zeros((end_date - start_date).days + 2)
old_lines = numpy.zeros_like(new_lines)
for day, devs in days.items():
for stats in devs.values():
new_lines[day] += stats.Added
old_lines[day] += stats.Removed + stats.Changed
resolution = 32
window = slepian(max(len(new_lines) // resolution, 1), 0.5)
new_lines = convolve(new_lines, window, "same")
old_lines = convolve(old_lines, window, "same")
matplotlib, pyplot = import_pyplot(args.backend, args.style)
plot_x = [start_date + timedelta(days=i) for i in range(len(new_lines))]
pyplot.fill_between(plot_x, new_lines, color="#8DB843", label="Changed new lines")
pyplot.fill_between(
plot_x, old_lines, color="#E14C35", label="Changed existing lines"
)
pyplot.legend(loc=2, fontsize=args.font_size)
for tick in chain(
pyplot.gca().xaxis.get_major_ticks(), pyplot.gca().yaxis.get_major_ticks()
):
tick.label.set_fontsize(args.font_size)
if args.mode == "all" and args.output:
output = get_plot_path(args.output, "old_vs_new")
else:
output = args.output
deploy_plot("Additions vs changes", output, args.background)
def plot_ownership(args, repo, names, people, date_range, last):
if args.output and args.output.endswith(".json"):
data = locals().copy()
del data["args"]
data["type"] = "ownership"
if args.mode == "all" and args.output:
output = get_plot_path(args.output, "people")
else:
output = args.output
with open(output, "w") as fout:
json.dump(data, fout, sort_keys=True, default=default_json)
return
matplotlib, pyplot = import_pyplot(args.backend, args.style)
polys = pyplot.stackplot(date_range, people, labels=names)
if names[-1] == "others":
polys[-1].set_hatch("/")
pyplot.xlim(parse_date(args.start_date, date_range[0]),
parse_date(args.end_date, last))
if args.relative:
for i in range(people.shape[1]):
people[:, i] /= people[:, i].sum()
pyplot.ylim(0, 1)
legend_loc = 3
else:
legend_loc = 2
ncol = 1 if len(names) < 15 else 2
legend = pyplot.legend(loc=legend_loc, fontsize=args.font_size, ncol=ncol)
apply_plot_style(pyplot.gcf(), pyplot.gca(), legend, args.background,
args.font_size, args.size)
if args.mode == "all" and args.output:
output = get_plot_path(args.output, "people")
else:
output = args.output
deploy_plot("%s code ownership through time" % repo, output,
args.background)
def plot_burndown(
args: Namespace,
target: str,
name: str,
matrix: numpy.ndarray,
date_range_sampling: 'DatetimeIndex',
labels: List[int],
granularity: int,
sampling: int,
resample: str,
) -> None:
if args.output and args.output.endswith(".json"):
data = locals().copy()
del data["args"]
data["type"] = "burndown"
if args.mode == "project" and target == "project":
output = args.output
else:
if target == "project":
name = "project"
output = get_plot_path(args.output, name)
with open(output, "w") as fout:
json.dump(data, fout, sort_keys=True, default=default_json)
return
matplotlib, pyplot = import_pyplot(args.backend, args.style)
pyplot.stackplot(date_range_sampling, matrix, labels=labels)
if args.relative:
for i in range(matrix.shape[1]):
matrix[:, i] /= matrix[:, i].sum()
pyplot.ylim(0, 1)
legend_loc = 3
else:
legend_loc = 2
legend = pyplot.legend(loc=legend_loc, fontsize=args.font_size)
pyplot.ylabel("Lines of code")
pyplot.xlabel("Time")
apply_plot_style(pyplot.gcf(), pyplot.gca(), legend, args.background,
args.font_size, args.size)
pyplot.xlim(
parse_date(args.start_date, date_range_sampling[0]),
parse_date(args.end_date, date_range_sampling[-1]),
)
locator = pyplot.gca().xaxis.get_major_locator()
# set the optimal xticks locator
if "M" not in resample:
pyplot.gca().xaxis.set_major_locator(matplotlib.dates.YearLocator())
locs = pyplot.gca().get_xticks().tolist()
if len(locs) >= 16:
pyplot.gca().xaxis.set_major_locator(matplotlib.dates.YearLocator())
locs = pyplot.gca().get_xticks().tolist()
if len(locs) >= 16:
pyplot.gca().xaxis.set_major_locator(locator)
if locs[0] < pyplot.xlim()[0]:
del locs[0]
endindex = -1
if len(locs) >= 2 and pyplot.xlim()[1] - locs[-1] > (locs[-1] -
locs[-2]) / 2:
locs.append(pyplot.xlim()[1])
endindex = len(locs) - 1
startindex = -1
if len(locs) >= 2 and locs[0] - pyplot.xlim()[0] > (locs[1] - locs[0]) / 2:
locs.append(pyplot.xlim()[0])
startindex = len(locs) - 1
pyplot.gca().set_xticks(locs)
# hacking time!
labels = pyplot.gca().get_xticklabels()
if startindex >= 0:
labels[startindex].set_text(date_range_sampling[0].date())
labels[startindex].set_text = lambda _: None
labels[startindex].set_rotation(30)
labels[startindex].set_ha("right")
if endindex >= 0:
labels[endindex].set_text(date_range_sampling[-1].date())
labels[endindex].set_text = lambda _: None
labels[endindex].set_rotation(30)
labels[endindex].set_ha("right")
title = "%s %d x %d (granularity %d, sampling %d)" % (
(name, ) + matrix.shape + (granularity, sampling))
output = args.output
if output:
if args.mode == "project" and target == "project":
output = args.output
else:
if target == "project":
name = "project"
output = get_plot_path(args.output, name)
deploy_plot(title, output, args.background)
def show_devs_efforts(
args: Namespace,
name: str,
start_date: int,
end_date: int,
people: List[str],
days: Dict[int, Dict[int, DevDay]],
max_people: int,
) -> None:
from scipy.signal import convolve, slepian
start_date = datetime.fromtimestamp(start_date)
start_date = datetime(start_date.year, start_date.month, start_date.day)
end_date = datetime.fromtimestamp(end_date)
end_date = datetime(end_date.year, end_date.month, end_date.day)
efforts_by_dev = defaultdict(int)
for day, devs in days.items():
for dev, stats in devs.items():
efforts_by_dev[dev] += stats.Added + stats.Removed + stats.Changed
if len(efforts_by_dev) > max_people:
chosen = {
v
for k, v in sorted(
((v, k) for k, v in efforts_by_dev.items()), reverse=True
)[:max_people]
}
print("Warning: truncated people to the most active %d" % max_people)
else:
chosen = set(efforts_by_dev)
chosen_efforts = sorted(((efforts_by_dev[k], k) for k in chosen), reverse=True)
chosen_order = {k: i for i, (_, k) in enumerate(chosen_efforts)}
efforts = numpy.zeros(
(len(chosen) + 1, (end_date - start_date).days + 1), dtype=numpy.float32
)
for day, devs in days.items():
if day < efforts.shape[1]:
for dev, stats in devs.items():
dev = chosen_order.get(dev, len(chosen_order))
efforts[dev][day] += stats.Added + stats.Removed + stats.Changed
efforts_cum = numpy.cumsum(efforts, axis=1)
window = slepian(10, 0.5)
window /= window.sum()
for e in (efforts, efforts_cum):
for i in range(e.shape[0]):
ending = e[i][-len(window) * 2 :].copy()
e[i] = convolve(e[i], window, "same")
e[i][-len(ending) :] = ending
matplotlib, pyplot = import_pyplot(args.backend, args.style)
plot_x = [start_date + timedelta(days=i) for i in range(efforts.shape[1])]
people = [people[k] for _, k in chosen_efforts] + ["others"]
for i, name in enumerate(people):
if len(name) > 40:
people[i] = name[:37] + "..."
polys = pyplot.stackplot(plot_x, efforts_cum, labels=people)
if len(polys) == max_people + 1:
polys[-1].set_hatch("/")
polys = pyplot.stackplot(plot_x, -efforts * efforts_cum.max() / efforts.max())
if len(polys) == max_people + 1:
polys[-1].set_hatch("/")
yticks = []
for tick in pyplot.gca().yaxis.iter_ticks():
if tick[1] >= 0:
yticks.append(tick[1])
pyplot.gca().yaxis.set_ticks(yticks)
legend = pyplot.legend(loc=2, ncol=2, fontsize=args.font_size)
apply_plot_style(
pyplot.gcf(),
pyplot.gca(),
legend,
args.background,
args.font_size,
args.size or "16,10",
)
if args.mode == "all" and args.output:
output = get_plot_path(args.output, "efforts")
else:
output = args.output
deploy_plot("Efforts through time (changed lines of code)", output, args.background)
def show_devs(
args: Namespace,
name: str,
start_date: int,
end_date: int,
people: List[str],
days: Dict[int, Dict[int, DevDay]],
max_people: int = 50,
) -> None:
from scipy.signal import convolve, slepian
if len(people) > max_people:
print("Picking top %s developers by commit count" % max_people)
# pick top N developers by commit count
commits = defaultdict(int)
for devs in days.values():
for dev, stats in devs.items():
commits[dev] += stats.Commits
commits = sorted(((v, k) for k, v in commits.items()), reverse=True)
chosen_people = {people[k] for _, k in commits[:max_people]}
else:
chosen_people = set(people)
dists, devseries, devstats, route = order_commits(chosen_people, days, people)
route_map = {v: i for i, v in enumerate(route)}
# determine clusters
clusters = hdbscan_cluster_routed_series(dists, route)
keys = list(devseries.keys())
route = [keys[node] for node in route]
print("Plotting")
# smooth time series
start_date = datetime.fromtimestamp(start_date)
start_date = datetime(start_date.year, start_date.month, start_date.day)
end_date = datetime.fromtimestamp(end_date)
end_date = datetime(end_date.year, end_date.month, end_date.day)
size = (end_date - start_date).days + 1
plot_x = [start_date + timedelta(days=i) for i in range(size)]
resolution = 64
window = slepian(size // resolution, 0.5)
final = numpy.zeros((len(devseries), size), dtype=numpy.float32)
for i, s in enumerate(devseries.values()):
arr = numpy.array(s).transpose()
full_history = numpy.zeros(size, dtype=numpy.float32)
mask = arr[0] < size
full_history[arr[0][mask]] = arr[1][mask]
final[route_map[i]] = convolve(full_history, window, "same")
matplotlib, pyplot = import_pyplot(args.backend, args.style)
pyplot.rcParams["figure.figsize"] = (32, 16)
pyplot.rcParams["font.size"] = args.font_size
prop_cycle = pyplot.rcParams["axes.prop_cycle"]
colors = prop_cycle.by_key()["color"]
fig, axes = pyplot.subplots(final.shape[0], 1)
backgrounds = (
("#C4FFDB", "#FFD0CD") if args.background == "white" else ("#05401C", "#40110E")
)
max_cluster = numpy.max(clusters)
for ax, series, cluster, dev_i in zip(axes, final, clusters, route):
if cluster >= 0:
color = colors[cluster % len(colors)]
i = 1
while color == "#777777":
color = colors[(max_cluster + i) % len(colors)]
i += 1
else:
# outlier
color = "#777777"
ax.fill_between(plot_x, series, color=color)
ax.set_axis_off()
author = people[dev_i]
ax.text(
0.03,
0.5,
author[:36] + (author[36:] and "..."),
horizontalalignment="right",
verticalalignment="center",
transform=ax.transAxes,
fontsize=args.font_size,
color="black" if args.background == "white" else "white",
)
ds = devstats[dev_i]
stats = "%5d %8s %8s" % (
ds[0],
_format_number(ds[1] - ds[2]),
_format_number(ds[3]),
)
ax.text(
0.97,
0.5,
stats,
horizontalalignment="left",
verticalalignment="center",
transform=ax.transAxes,
fontsize=args.font_size,
family="monospace",
backgroundcolor=backgrounds[ds[1] <= ds[2]],
color="black" if args.background == "white" else "white",
)
axes[0].text(
0.97,
1.75,
" cmts delta changed",
horizontalalignment="left",
verticalalignment="center",
transform=axes[0].transAxes,
fontsize=args.font_size,
family="monospace",
color="black" if args.background == "white" else "white",
)
axes[-1].set_axis_on()
target_num_labels = 12
num_months = (
(end_date.year - start_date.year) * 12 + end_date.month - start_date.month
)
interval = int(numpy.ceil(num_months / target_num_labels))
if interval >= 8:
interval = int(numpy.ceil(num_months / (12 * target_num_labels)))
axes[-1].xaxis.set_major_locator(
matplotlib.dates.YearLocator(base=max(1, interval // 12))
)
axes[-1].xaxis.set_major_formatter(matplotlib.dates.DateFormatter("%Y"))
else:
axes[-1].xaxis.set_major_locator(
matplotlib.dates.MonthLocator(interval=interval)
)
axes[-1].xaxis.set_major_formatter(matplotlib.dates.DateFormatter("%Y-%m"))
for tick in axes[-1].xaxis.get_major_ticks():
tick.label.set_fontsize(args.font_size)
axes[-1].spines["left"].set_visible(False)
axes[-1].spines["right"].set_visible(False)
axes[-1].spines["top"].set_visible(False)
axes[-1].get_yaxis().set_visible(False)
axes[-1].set_facecolor((1.0,) * 3 + (0.0,))
title = ("%s commits" % name) if not args.output else ""
if args.mode == "all" and args.output:
output = get_plot_path(args.output, "time_series")
else:
output = args.output
deploy_plot(title, output, args.background)
def show_sentiment_stats(args, name, resample, start_date, data):
from scipy.signal import convolve, slepian
matplotlib, pyplot = import_pyplot(args.backend, args.style)
start_date = datetime.fromtimestamp(start_date)
data = sorted(data.items())
mood = numpy.zeros(data[-1][0] + 1, dtype=numpy.float32)
timeline = numpy.array(
[start_date + timedelta(days=i) for i in range(mood.shape[0])]
)
for d, val in data:
mood[d] = (0.5 - val.Value) * 2
resolution = 32
window = slepian(len(timeline) // resolution, 0.5)
window /= window.sum()
mood_smooth = convolve(mood, window, "same")
pos = mood_smooth.copy()
pos[pos < 0] = 0
neg = mood_smooth.copy()
neg[neg >= 0] = 0
resolution = 4
window = numpy.ones(len(timeline) // resolution)
window /= window.sum()
avg = convolve(mood, window, "same")
pyplot.fill_between(timeline, pos, color="#8DB843", label="Positive")
pyplot.fill_between(timeline, neg, color="#E14C35", label="Negative")
pyplot.plot(timeline, avg, color="grey", label="Average", linewidth=5)
legend = pyplot.legend(loc=1, fontsize=args.font_size)
pyplot.ylabel("Comment sentiment")
pyplot.xlabel("Time")
apply_plot_style(
pyplot.gcf(), pyplot.gca(), legend, args.background, args.font_size, args.size
)
pyplot.xlim(
parse_date(args.start_date, timeline[0]),
parse_date(args.end_date, timeline[-1]),
)
locator = pyplot.gca().xaxis.get_major_locator()
# set the optimal xticks locator
if "M" not in resample:
pyplot.gca().xaxis.set_major_locator(matplotlib.dates.YearLocator())
locs = pyplot.gca().get_xticks().tolist()
if len(locs) >= 16:
pyplot.gca().xaxis.set_major_locator(matplotlib.dates.YearLocator())
locs = pyplot.gca().get_xticks().tolist()
if len(locs) >= 16:
pyplot.gca().xaxis.set_major_locator(locator)
if locs[0] < pyplot.xlim()[0]:
del locs[0]
endindex = -1
if len(locs) >= 2 and pyplot.xlim()[1] - locs[-1] > (locs[-1] - locs[-2]) / 2:
locs.append(pyplot.xlim()[1])
endindex = len(locs) - 1
startindex = -1
if len(locs) >= 2 and locs[0] - pyplot.xlim()[0] > (locs[1] - locs[0]) / 2:
locs.append(pyplot.xlim()[0])
startindex = len(locs) - 1
pyplot.gca().set_xticks(locs)
# hacking time!
labels = pyplot.gca().get_xticklabels()
if startindex >= 0:
labels[startindex].set_text(timeline[0].date())
labels[startindex].set_text = lambda _: None
labels[startindex].set_rotation(30)
labels[startindex].set_ha("right")
if endindex >= 0:
labels[endindex].set_text(timeline[-1].date())
labels[endindex].set_text = lambda _: None
labels[endindex].set_rotation(30)
labels[endindex].set_ha("right")
overall_pos = sum(2 * (0.5 - d[1].Value) for d in data if d[1].Value < 0.5)
overall_neg = sum(2 * (d[1].Value - 0.5) for d in data if d[1].Value > 0.5)
title = "%s sentiment +%.1f -%.1f δ=%.1f" % (
name,
overall_pos,
overall_neg,
overall_pos - overall_neg,
)
if args.mode == "all" and args.output:
output = get_plot_path(args.output, "sentiment")
else:
output = args.output
deploy_plot(title, output, args.background)