def create_length_plot(len_df, legend_position='right', legend_box='vertical'):
mean_len_df = len_df.groupby(['Task', 'Method']).mean().reset_index()
mean_len_df[' '] = 'Mean Length'
plt = (ggplot(len_df) + aes(x='x', fill='Method', y='..density..') +
geom_histogram(binwidth=2, position='identity', alpha=.6) +
geom_text(aes(x='x', y=.22, label='x', color='Method'),
mean_len_df,
inherit_aes=False,
format_string='{:.1f}',
show_legend=False) +
geom_segment(aes(x='x', xend='x', y=0, yend=.205, linetype=' '),
mean_len_df,
inherit_aes=False,
color='black') + scale_linetype_manual(['dashed']) +
facet_wrap('Task') + xlim(0, 20) + ylim(0, .23) +
xlab('Example Length') + ylab('Frequency') +
scale_color_manual(values=COLORS) +
scale_fill_manual(values=COLORS) + theme_fs() + theme(
aspect_ratio=1,
legend_title=element_blank(),
legend_position=legend_position,
legend_box=legend_box,
))
return plt
def test_scale_linetype_strings_tuples():
# linetype_manual accepts tuples as mapping results
# this must be tested specifically.
df = pd.DataFrame({
"x": [0, 1, 0, 1, 0, 1],
"y": [0, 1, 0, 2, 0, 3],
"lt": ["A", "A", "B", "B", "C", "C"],
})
p = ggplot(df)
p += geom_line(aes(x="x", y="y", ymax="y+1", linetype="lt", group="lt"))
p += scale_linetype_manual(values=['solid', 'dashed', 'dotted'])
assert p == "scale_linetype_manual_strings"
def test_scale_linetype_manual_tuples():
# linetype_manual accepts tuples as mapping results
# this must be tested specifically.
df = pd.DataFrame({
"x": [0, 1, 0, 1, 0, 1],
"y": [0, 1, 0, 2, 0, 3],
"lt": ["A", "A", "B", "B", "C", "C"],
})
p = ggplot(df)
p += geom_line(aes(x="x", y="y", ymax="y+1", linetype="lt", group="lt"))
p += scale_linetype_manual(values=(
(2, (5, 3, 1, 3)),
(1, (10, 2)),
(1, (1, 2)),
))
assert p == "scale_linetype_manual_tuples"
def create_length_plot(len_df, legend_position='right', legend_box='vertical'):
mean_len_df = len_df.groupby(['Task', 'Method']).mean().reset_index()
mean_len_df[' '] = 'Mean Length'
plt = (
ggplot(len_df)
+ aes(x='x', fill='Method', y='..density..')
+ geom_histogram(binwidth=2, position='identity', alpha=.6)
+ geom_text(
aes(x='x', y=.22, label='x', color='Method'),
mean_len_df,
inherit_aes=False,
format_string='{:.1f}',
show_legend=False
)
+ geom_segment(
aes(x='x', xend='x', y=0, yend=.205, linetype=' '),
mean_len_df,
inherit_aes=False, color='black'
)
+ scale_linetype_manual(['dashed'])
+ facet_wrap('Task')
+ xlim(0, 20) + ylim(0, .23)
+ xlab('Example Length') + ylab('Frequency')
+ scale_color_manual(values=COLORS)
+ scale_fill_manual(values=COLORS)
+ theme_fs()
+ theme(
aspect_ratio=1,
legend_title=element_blank(),
legend_position=legend_position,
legend_box=legend_box,
)
)
return plt
def plot_xbs(df, group, var, n_side=9, n_delta=6):
r"""Construct Xbar and S chart
Construct an Xbar and S chart to assess the state of statistical control of
a dataset.
Args:
df (DataFrame): Data to analyze
group (str): Variable for grouping
var (str): Variable to study
Keyword args:
n_side (int): Number of consecutive runs above/below centerline to flag
n_delta (int): Number of consecutive runs increasing/decreasing to flag
Returns:
plotnine object: Xbar and S chart
Examples::
import grama as gr
DF = gr.Intention()
from grama.data import df_shewhart
(
df_shewhart
>> gr.tf_mutate(idx=DF.index // 10)
>> gr.pt_xbs("idx", "tensile_strength")
)
"""
## Prepare the data
DF = Intention()
df_batched = (df >> tf_group_by(group) >> tf_summarize(
X=mean(DF[var]),
S=sd(DF[var]),
n=nfcn(DF.index),
) >> tf_ungroup())
df_stats = (df_batched >> tf_summarize(
X_center=mean(DF.X),
S_biased=mean(DF.S),
n=mean(DF.n),
))
n = df_stats.n[0]
df_stats["S_center"] = df_stats.S_biased / c_sd(n)
df_stats["X_LCL"] = df_stats.X_center - 3 * df_stats.S_center / sqrt(n)
df_stats["X_UCL"] = df_stats.X_center + 3 * df_stats.S_center / sqrt(n)
df_stats["S_LCL"] = B3(n) * df_stats.S_center
df_stats["S_UCL"] = B4(n) * df_stats.S_center
## Reshape for plotting
df_stats_long = (df_stats >> tf_pivot_longer(
columns=["X_LCL", "X_center", "X_UCL", "S_LCL", "S_center", "S_UCL"],
names_to=["_var", "_stat"],
names_sep="_",
values_to="_value",
))
# Fake group value to avoid issue with discrete group variable
df_stats_long[group] = [df_batched[group].values[0]
] * df_stats_long.shape[0]
df_batched_long = (
df_batched >> tf_pivot_longer(
columns=["X", "S"],
names_to="_var",
values_to="_value",
)
## Flag patterns
>> tf_left_join(
df_stats >> tf_pivot_longer(
columns=[
"X_LCL", "X_center", "X_UCL", "S_LCL", "S_center", "S_UCL"
],
names_to=["_var", ".value"],
names_sep="_",
),
by="_var",
) >> tf_group_by("_var") >> tf_mutate(
outlier_below=(DF._value < DF.LCL), # Outside control limits
outlier_above=(DF.UCL < DF._value),
below=consec(DF._value < DF.center, i=n_side), # Below mean
above=consec(DF.center < DF._value, i=n_side), # Above mean
) >> tf_mutate(
decreasing=consec((lead(DF._value) - DF._value) < 0, i=n_delta - 1)
| # Decreasing
consec((DF._value - lag(DF._value)) < 0, i=n_delta - 1),
increasing=consec(0 < (lead(DF._value) - DF._value), i=n_delta - 1)
| # Increasing
consec(0 < (DF._value - lag(DF._value)), i=n_delta - 1),
) >> tf_mutate(
sign=case_when([DF.outlier_below, "-2"], [DF.outlier_above, "+2"],
[DF.below | DF.decreasing, "-1"],
[DF.above | DF.increasing, "+1"], [True, "0"]),
glyph=case_when(
[DF.outlier_below, "Below Limit"],
[DF.outlier_above, "Above Limit"],
[DF.below, "Low Run"],
[DF.above, "High Run"],
[DF.increasing, "Increasing Run"],
[DF.decreasing, "Decreasing Run"],
[True, "None"],
)) >> tf_ungroup())
## Visualize
return (df_batched_long >> ggplot(aes(x=group)) + geom_hline(
data=df_stats_long,
mapping=aes(yintercept="_value", linetype="_stat"),
) + geom_line(aes(y="_value", group="_var"), size=0.2) + geom_point(
aes(y="_value", color="sign", shape="glyph"),
size=3,
) + scale_color_manual(values={
"-2": "blue",
"-1": "darkturquoise",
"0": "black",
"+1": "salmon",
"+2": "red"
}, ) + scale_shape_manual(
name="Patterns",
values={
"Below Limit": "s",
"Above Limit": "s",
"Low Run": "X",
"High Run": "X",
"Increasing Run": "^",
"Decreasing Run": "v",
"None": "."
},
) + scale_linetype_manual(
name="Guideline",
values=dict(LCL="dashed", UCL="dashed", center="solid"),
) + guides(color=None) + facet_grid(
"_var~.",
scales="free_y",
labeller=labeller(dict(X="Mean", S="Variability")),
) + labs(
x="Group variable ({})".format(group),
y="Value ({})".format(var),
))
"2020ML": "#33a02c",
"2020": "#1f78b4",
}
g = (
p9.ggplot(publish_rate_df.rename(index=str, columns={"label": "Label"})) +
p9.aes(
x="pub_month",
y="rate",
fill="Label",
group="Label",
color="Label",
linetype="Label",
shape="Label",
) + p9.geom_point(size=2) + p9.geom_line() +
p9.scale_linetype_manual(["solid", "solid", "solid"]) +
p9.scale_color_manual(
[color_mapper["2020"], color_mapper["2020ML"], color_mapper["2018"]]) +
p9.scale_fill_manual(
[color_mapper["2020"], color_mapper["2020ML"], color_mapper["2018"]]) +
p9.scale_shape_manual(["o", "o", "o"])
# plot the x axis titles
+ p9.geom_vline(xintercept=[2.5, 14.5, 26.5, 38.5, 50.5, 62.5, 74.5]) +
p9.geom_text(label="2014", x=8.5, y=0, color="black", size=13) +
p9.geom_text(label="2015", x=20.5, y=0, color="black", size=13) +
p9.geom_text(label="2016", x=32.5, y=0, color="black", size=13) +
p9.geom_text(label="2017", x=44.5, y=0, color="black", size=13) +
p9.geom_text(label="2018", x=56.5, y=0, color="black", size=13) +
p9.geom_text(label="2019", x=68.5, y=0, color="black", size=13)
# Plot the overall proportion published
+ p9.geom_hline(
"2020ML": "#33a02c",
"2020": "#1f78b4",
}
# In[21]:
g = (
p9.ggplot(publish_rate_df.rename(index=str, columns={"label": "Label"})) +
p9.aes(x="pub_month",
y="rate",
fill="Label",
group="Label",
color="Label",
linetype="Label",
shape="Label") + p9.geom_point(size=2) + p9.geom_line() +
p9.scale_linetype_manual(['solid', 'solid', 'solid']) +
p9.scale_color_manual(
[color_mapper['2020'], color_mapper['2020ML'], color_mapper['2018']]) +
p9.scale_fill_manual(
[color_mapper['2020'], color_mapper['2020ML'], color_mapper['2018']]) +
p9.scale_shape_manual(['o', 'o', 'o'])
# plot the x axis titles
+ p9.geom_vline(xintercept=[2.5, 14.5, 26.5, 38.5, 50.5, 62.5, 74.5]) +
p9.geom_text(label="2014", x=8.5, y=0, color="black") +
p9.geom_text(label="2015", x=20.5, y=0, color="black") +
p9.geom_text(label="2016", x=32.5, y=0, color="black") +
p9.geom_text(label="2017", x=44.5, y=0, color="black") +
p9.geom_text(label="2018", x=56.5, y=0, color="black") +
p9.geom_text(label="2019", x=68.5, y=0, color="black")