def analyze_kimura_distances(env, df):
# type: (Environment, pd.DataFrame) -> None
pd_work = env["pd-work"]
df = df[df["Kimura-to-query"] != "[]"].copy()
df["Kimura-to-query"] = df["Kimura-to-query"].apply(ast.literal_eval)
df["Average-Kimura"] = df["Kimura-to-query"].apply(np.mean)
df["Std-Kimura"] = df["Kimura-to-query"].apply(np.std)
sns.lmplot(df,
"Genome GC",
"Average-Kimura",
hue="Ancestor",
sns_kwargs={
"scatter": False,
"lowess": True,
"scatter_kws": {
"s": 5
},
"palette": CM.get_map("ancestor")
},
figure_options=FigureOptions(save_fig=next_name(pd_work)))
df_mean = df.groupby(["Ancestor", "GCFID"], as_index=False).mean()
sns.lmplot(df_mean,
"Genome GC",
"Average-Kimura",
hue="Ancestor",
sns_kwargs={
"scatter": True,
"lowess": True,
"scatter_kws": {
"s": 5
},
"palette": CM.get_map("ancestor")
},
figure_options=FigureOptions(save_fig=next_name(pd_work)))
# Min/max kimura
df["Min-Kimura"] = df["Kimura-to-query"].apply(min)
df["Max-Kimura"] = df["Kimura-to-query"].apply(max)
contour_kimura_per_ancestor(env, df)
one_dim_Kimura_accuracy(env, df)
kimura_dist_plot(env, df)
heat_map_Kimura_accuracy(env,
df,
"Min-Kimura",
"Max-Kimura",
balance=True,
xlabel="Minimum Kimura",
ylabel="Maximum Kimura")
heat_map_Kimura_accuracy(env,
df,
"Average-Kimura",
"Std-Kimura",
balance=False)
def analyze_gms2_components_on_verified_set(env, gil):
# type: (Environment, GenomeInfoList) -> None
# run different components
list_df = list()
for gi in gil:
list_df.append(
analyze_gms2_components_on_verified_set_for_gi(env, gi)
)
df = pd.concat(list_df, ignore_index=True, sort=False)
df["Genome"] = df.apply(fix_names, axis=1)
print(df.to_csv())
fig, ax = plt.subplots(figsize=(12,4))
sns.barplot(df, "Genome", "Error", hue="Component",
ax=ax,
figure_options=FigureOptions(
save_fig=next_name(env["pd-work"])
),
sns_kwargs={
"hue_order": reversed(["GMS2", "MGM2*", "Start Context", "RBS", "Start Codons", "Promoter", "MGM"]),
"palette": CM.get_map("gms2_components")
})
def kimura_dist_plot(env, df):
import seaborn
import matplotlib.pyplot as plt
ancestors = list(set(df["Ancestor"]))
# fig, axes = plt.subplots(2, math.ceil(len(ancestors)/2), sharex=True, sharey=True)
#
# for anc, ax in zip(ancestors, axes.ravel()):
#
# df_group = df[df["Ancestor"] == anc]
# seaborn.distplot(df_group["Average-Kimura"], ax=ax, color=CM.get_map("ancestor")[anc],
# hist=False)
# ax.set_title(anc)
# plt.show()
fig, ax = plt.subplots() # type: plt.Figure, plt.Axes
for anc in ancestors:
df_group = df[df["Ancestor"] == anc]
seaborn.distplot(df_group["Average-Kimura"],
ax=ax,
color=CM.get_map("ancestor")[anc],
hist=False,
label=anc)
# ax.set_title(anc)
ax.legend(ancestors)
ax.set_ylabel("PDF")
save_figure(FigureOptions(save_fig=next_name(env["pd-work"])))
plt.show()
def main(env, args):
# type: (Environment, argparse.Namespace) -> None
df = pd.read_csv(args.pf_input, header=0)
add_percentages(df)
sns.set_context(context="paper", font_scale=1.5)
#clean up
df = df[df["Total Candidates"] < 100]
colors = ["windows blue", "amber", "faded green", "dusty purple"]
palette = sns.xkcd_palette(colors)
sns.palplot(palette)
plt.show()
sns.set_palette(palette)
fig_num = 0
plt.figure(figsize=(12, 4))
sns.jointplot(x="gc", y="Total Candidates", data=df)
# plt.legend(loc='center left', bbox_to_anchor=(1.05, 0.5))
plt.savefig(os.path.join(env["pd-work"], "{}.pdf".format(fig_num)),
bbox_inches='tight')
plt.show()
fig_num += 1
# Average number of candidates per GC
df_tmp = df.groupby(["gcfid", "ancestor"], as_index=False).agg("mean")
plt.figure(figsize=(12, 4))
g = sns.scatterplot(x="gc",
y="Total Candidates",
data=df_tmp,
hue="ancestor",
palette=CM.get_map("ancestor"))
plt.legend(loc='center left', bbox_to_anchor=(1.05, 0.5))
g.set(ylabel="Average number of candidates")
g.set(xlabel="GC")
plt.savefig(os.path.join(env["pd-work"], "{}.pdf".format(fig_num)),
bbox_inches='tight')
plt.show()
fig_num += 1
# Average number of candidates per GC
plt.figure(figsize=(12, 4))
g = sns.lmplot(x="gc",
y="Total Candidates",
data=df_tmp,
hue="ancestor",
aspect=2,
legend=False,
ci=None,
lowess=True,
palette=CM.get_map("ancestor"))
plt.legend(loc='center left', bbox_to_anchor=(1.05, 0.5))
g.set(ylabel="Average number of candidates")
g.set(xlabel="GC")
plt.savefig(os.path.join(env["pd-work"], "{}.pdf".format(fig_num)),
bbox_inches='tight')
plt.show()
fig_num += 1
pass
def analyze_upstream_distances(env, df):
# type: (Environment, pd.DataFrame) -> None
pd_work = os_join(env["pd-work"], "upstream_distances")
mkdir_p(pd_work)
# remove empty lists
df = df[df["Upstream-distance"] != "[]"].copy()
df["Upstream-distance"] = df["Upstream-distance"].apply(ast.literal_eval)
df["Most frequent upstream"] = df["Upstream-distance"].apply(most_frequent)
# compute consistencies with different flexibilities
for flexibility in {0, 3}:
df["PC(x,{})".format(flexibility)] = df[[
"Most frequent upstream", "Upstream-distance"
]].apply(lambda r: compute_consistency(r["Upstream-distance"], r[
"Most frequent upstream"], flexibility),
axis=1)
df = df[df["Support"] > 10].copy()
# for mf in range(-20, 50):
# df_mf = df[df["Most frequent upstream"] == mf]
# if len(df_mf) < 50:
# continue
#
# sns.distplot(df_mf, "PC(x,0)", figure_options=FigureOptions(
# title="PC({},{})".format(mf, 0),
# save_fig=next_name(pd_work),
# xlim=(0,1)
# ))
# sns.distplot(df_mf, "PC(x,3)", figure_options=FigureOptions(
# title="PC({},{})".format(mf, 3),
# save_fig=next_name(pd_work),
# xlim=(0, 1)
# ))
# plot distribution of Average PC
import seaborn
import matplotlib.pyplot as plt
df_tmp = df[(df["Support"] > 10) & (df["Most frequent upstream"] < 100) &
(df["Most frequent upstream"] > -50)]
# NCBI consistency as a func
df = df[(df["Support"] > 10) & (df["GMS2=SBSP"]) &
(df["Most frequent upstream"] < 100) &
(df["Most frequent upstream"] > -50)]
df_tmp = stack_columns_as_rows(
df_tmp[["Most frequent upstream", "PC(x,0)", "PC(x,3)",
"Ancestor"]], ["PC(x,0)", "PC(x,3)"],
"PC(x,f)",
None,
label_col="Flexibility")
# seaborn.lmplot("Most frequent upstream", "PC(x,f)", df_tmp,
# scatter=False, hue="Flexibility", lowess=True)
# plt.show()
#
# seaborn.lmplot("Most frequent upstream", "PC(x,f)", df_tmp,
# hue="Flexibility", lowess=True)
# plt.show()
#
# seaborn.lmplot("Most frequent upstream", "PC(x,f)", df_tmp,
# scatter=False, hue="Flexibility")
# plt.show()
sns.lmplot(df_tmp,
"Most frequent upstream",
"PC(x,f)",
hue="Flexibility",
sns_kwargs={
"scatter": False,
"lowess": True
},
figure_options=FigureOptions(save_fig=next_name(pd_work),
xlim=[-7, None],
ylim=[0, 1]))
sns.distplot(df,
"Most frequent upstream",
figure_options=FigureOptions(save_fig=next_name(pd_work)),
sns_kwargs={"kde": True})
import seaborn
# seaborn.countplot("Most frequent upstream", data=df[(df["Most frequent upstream"] < 10) & (df["Most frequent upstream"] > -10)], hue="Ancestor")
(df[(df["Most frequent upstream"] < 10)
& (df["Most frequent upstream"] > -10)].groupby("Ancestor")
["Most frequent upstream"].value_counts(normalize=True).mul(100).rename(
'Percentage (by clade)').reset_index().pipe(
(seaborn.catplot, 'data'),
x="Most frequent upstream",
y='Percentage (by clade)',
hue="Ancestor",
kind='point',
scale=0.5,
legend=False,
palette=CM.get_map("ancestor"),
aspect=1.5))
plt.legend(loc="best", title="Clade")
figure_options = FigureOptions(
save_fig=next_name(pd_work),
xlabel="Most frequent distance to upstream gene",
ylabel="Percent of components (by clade)")
plt.xlabel(figure_options.xlabel)
plt.ylabel(figure_options.ylabel)
save_figure(figure_options)
plt.show()
(df[(df["Most frequent upstream"] < 10)
& (df["Most frequent upstream"] > -10)].groupby("Ancestor")
["Most frequent upstream"].value_counts().rename(
'number').reset_index().pipe((seaborn.catplot, 'data'),
x="Most frequent upstream",
y='number',
hue="Ancestor",
kind='point',
scale=0.5,
legend=False,
palette=CM.get_map("ancestor"),
aspect=1.5))
plt.legend(loc="best", title="Clade")
figure_options = FigureOptions(
save_fig=next_name(pd_work),
xlabel="Most frequent distance to upstream gene",
ylabel="Number of components")
plt.xlabel(figure_options.xlabel)
plt.ylabel(figure_options.ylabel)
save_figure(figure_options)
plt.show()
f, ax1 = plt.subplots()
ax2 = ax1.twinx()
for ancestor, df_group in df.groupby("Ancestor"):
seaborn.distplot(df_group["Most frequent upstream"], kde=False, ax=ax1)
# ax2.set_ylim(0, 3)
ax2.yaxis.set_ticks([])
seaborn.kdeplot(df_group["Most frequent upstream"], ax=ax2)
ax1.set_xlabel('x var')
ax1.set_ylabel('Counts')
# g = seaborn.FacetGrid(df, hue="Ancestor")
# g = g.map(seaborn.distplot, "Most frequent upstream", hist=True)
plt.show()
print(df["Most frequent upstream"].value_counts(normalize=True))
sns.lmplot(
df,
"Most frequent upstream",
"PC(x,0)",
hue="Ancestor",
sns_kwargs={
"scatter": False,
"lowess": True,
"palette": CM.get_map("ancestor")
},
figure_options=FigureOptions(save_fig=next_name(pd_work),
xlim=[-7, None],
ylim=[0, 1]),
)
sns.lmplot(df,
"Most frequent upstream",
"PC(x,3)",
hue="Ancestor",
sns_kwargs={
"scatter": False,
"lowess": True,
"palette": CM.get_map("ancestor")
},
figure_options=FigureOptions(save_fig=next_name(pd_work),
xlim=[-7, None],
ylim=[0, 1]))
# NCBI sensitivity
# collect:
# average 5' per ancestor, r,
ranges = [(-5, 0), (0, 10), (10, 30), (30, 50), (50, 70)]
list_collect = list()
for r in ranges:
r_filter = (df["Most frequent upstream"] >=
r[0]) & (df["Most frequent upstream"] < r[1])
df_summary_per_gcfid = get_summary_per_gcfid(df[r_filter])
# viz_summary_per_gcfid(env, df_summary_per_gcfid, title=str(r))
df_summary_per_gcfid = df_summary_per_gcfid.groupby(
"Ancestor", as_index=False).mean()
df_summary_per_gcfid["Range"] = str(r)
list_collect.append(df_summary_per_gcfid)
df_tmp = pd.concat(list_collect, sort=False)
sns.catplot(df_tmp,
"Range",
"(GMS2=SBSP)!=NCBI % GMS2=SBSP",
hue="Ancestor",
kind="point",
sns_kwargs={"palette": CM.get_map("ancestor")})
sns.catplot(df_tmp,
"Range",
"GMS2=SBSP",
hue="Ancestor",
kind="point",
sns_kwargs={"palette": CM.get_map("ancestor")})
# do not average per gcfid - average per ancestor
list_collect = list()
range_avgs = list()
range_label = list()
for r in ranges:
r_filter = (df["Most frequent upstream"] >=
r[0]) & (df["Most frequent upstream"] < r[1])
df_r = df[r_filter]
for ancestor, df_group in df_r.groupby(
"Ancestor", as_index=False): # type: str, pd.DataFrame
f_gms2_eq_sbsp_with_ncbi_pred = (df_group["GMS2=SBSP"]) & (
df_group["NCBI"])
f_gms2_eq_sbsp_not_eq_ncbi = (f_gms2_eq_sbsp_with_ncbi_pred) & (
df_group["(GMS2=SBSP)!=NCBI"])
sensitivity = 100 * f_gms2_eq_sbsp_not_eq_ncbi.sum() / float(
f_gms2_eq_sbsp_with_ncbi_pred.sum())
list_collect.append({
"Ancestor":
ancestor,
"Range":
str(r),
"range_avg": (r[1] + r[0]) / 2.0,
"(GMS2=SBSP)!=NCBI % GMS2=SBSP":
sensitivity,
"GMS2=SBSP":
f_gms2_eq_sbsp_with_ncbi_pred.sum()
})
range_label.append(r)
range_avgs.append((r[1] + r[0]) / 2.0)
df_tmp = pd.DataFrame(list_collect)
sns.catplot(df_tmp,
"Range",
"(GMS2=SBSP)!=NCBI % GMS2=SBSP",
hue="Ancestor",
kind="point",
sns_kwargs={"palette": CM.get_map("ancestor")})
sns.catplot(df_tmp,
"Range",
"GMS2=SBSP",
hue="Ancestor",
kind="point",
sns_kwargs={"palette": CM.get_map("ancestor")})
ancestors = list(set(df_tmp["Ancestor"]))
fig, axes = plt.subplots(
len(ancestors),
1,
sharex="all",
)
for ancestor, ax in zip(ancestors, axes.ravel()): # type: str, plt.Axes
ax2 = ax.twinx()
curr_df = df_tmp[df_tmp["Ancestor"] == ancestor]
seaborn.lineplot("range_avg",
"(GMS2=SBSP)!=NCBI % GMS2=SBSP",
data=curr_df,
ax=ax)
seaborn.lineplot("range_avg",
"GMS2=SBSP",
data=curr_df,
color='r',
legend=False,
ax=ax2)
ax.set_ylabel(None)
ax2.set_ylabel(None)
ax.set_xlabel("Range Average")
plt.xticks(range_avgs, range_label)
plt.show()
fig, ax = plt.subplots()
ax2 = ax.twinx()
seaborn.lineplot("range_avg",
"(GMS2=SBSP)!=NCBI % GMS2=SBSP",
data=df_tmp,
ax=ax,
color="b",
ci=None,
hue="Ancestor")
seaborn.lineplot("range_avg",
"GMS2=SBSP",
data=df_tmp,
ci=None,
color='r',
legend=False,
ax=ax2,
hue="Ancestor")
# plt.xticks(range_avgs, range_label)
ax.set_ylim([0, None])
ax2.set_ylim([0, None])
ax.set_ylabel("NCBI 5' error rate vs GMS2=SBSP")
ax2.set_ylabel("Number of GMS2=SBSP genes")
ax.set_xlabel("Range Average")
ax.yaxis.label.set_color('b')
ax2.yaxis.label.set_color('r')
ax.set_xlabel("Distance to upstream gene (nt)")
plt.show()
# sbsp_geom_density(df, "Most frequent upstream", "GMS2=SBSP=NCBI", pd_work)
#
# for ancestor, df_group in df.groupby("Ancestor", as_index=False):
# sbsp_geom_density(df_group, "Most frequent upstream", "GMS2=SBSP=NCBI", pd_work, ancestor)
# sbsp_geom_density(df_group, "Support", "GMS2=SBSP=NCBI", pd_work, ancestor)
a = 0
def one_dim_Kimura_accuracy(env, df_all, num_steps=20):
# type: (Environment, pd.DataFrame, int) -> None
import matplotlib.pyplot as plt
pd_work = env["pd-work"]
ancestors = sorted(list(set(df_all["Ancestor"])))
# fig, axes = plt.subplots(2, math.ceil(len(ancestors) / 2), sharex=True, sharey=True)
# min_x = min(df_all["Average-Kimura"])
# max_x = max(df_all["Average-Kimura"]) + 0.000000001
# ss_x = (max_x - min_x) / float(num_steps)
#
# list_df = list()
# axis_idx = 0
# for ancestor, df in df_all.groupby("Ancestor", as_index=False):
# # ax = axes.ravel()[axis_idx]
# # axis_idx += 1
#
#
#
#
#
# import numpy as np
# gms2_eq_sbsp_and_ncbi = np.zeros(num_steps, dtype=float)
# gms2_eq_sbsp_eq_ncbi = np.zeros(num_steps, dtype=float)
#
# df_gms2_eq_sbsp_and_ncbi = (df["GMS2=SBSP"]) & (df["NCBI"])
# df_gms2_eq_sbsp_eq_ncbi = (df["GMS2=SBSP=NCBI"])
#
# for index in df.index:
#
# x_val = df.at[index, "Average-Kimura"]
#
# x_pos = int((x_val-min_x) / ss_x)
#
# gms2_eq_sbsp_and_ncbi[x_pos] += 1 if df.at[index, "GMS2=SBSP"] and df.at[index, "NCBI"] else 0
# gms2_eq_sbsp_eq_ncbi[x_pos] += 1 if df.at[index, "GMS2=SBSP=NCBI"] else 0
#
# accuracy = np.divide(gms2_eq_sbsp_eq_ncbi, gms2_eq_sbsp_and_ncbi)
# # accuracy = np.flip(accuracy, 0)
#
#
# xticks = list(range(0, num_steps))
#
# l_x = np.arange(min_x, max_x, ss_x)
# xticklabels = [round(l_x[i], 2) for i in xticks]
# # g = seaborn.heatmap(accuracy.transpose(), vmin=0, vmax=1, xticklabels=xticklabels, yticklabels=yticklabels, ax=ax,
# # cbar=True)
#
# # g = seaborn.lineplot(xticklabels, accuracy, ax=ax, label=ancestor)
#
# # cbar=g.cbar
#
# # g.set_xticks(xticks)
#
# curr_df = pd.DataFrame({
# "Average-Kimura": xticklabels,
# "Accuracy": accuracy,
# "Number-of-queries": gms2_eq_sbsp_and_ncbi
# })
# curr_df["Ancestor"] = ancestor
# list_df.append(curr_df)
#
# # g.set_xlabel("Min Kimura")
# # g.set_ylabel("Max Kimura")
# # g.set_title(ancestor)
#
# df = pd.concat(list_df) # type: pd.DataFrame
df = bin_data_one_d(env, df_all, "Average-Kimura", num_steps)
sns.lineplot(df,
"Average-Kimura",
"Accuracy",
hue="Ancestor",
figure_options=FigureOptions(save_fig=next_name(pd_work), ),
sns_kwargs={"palette": CM.get_map("ancestor")})
sns.lineplot(df,
"Average-Kimura",
"Number-of-queries",
hue="Ancestor",
figure_options=FigureOptions(save_fig=next_name(pd_work), ),
sns_kwargs={"palette": CM.get_map("ancestor")})
total_per_ancestor = {
ancestor: (df["Ancestor"].isin({ancestor})).sum()
for ancestor in ancestors
}
df["Percentage-of-queries"] = 0
df["Cumulative-percentage-of-queries"] = 0
df.reset_index(inplace=True)
for ancestor, df_group in df.groupby(
"Ancestor", as_index=False): # type: str, pd.DataFrame
df_group.sort_values("Average-Kimura", inplace=True)
index = df_group.index
prev = 0
total = df_group["Number-of-queries"].sum()
df.loc[index, "Percentage-of-queries"] = 100 * df.loc[
index, "Number-of-queries"] / float(total)
for i in index:
df.loc[i, "Cumulative-percentage-of-queries"] = prev + df.loc[
i, "Percentage-of-queries"]
prev = df.loc[i, "Cumulative-percentage-of-queries"]
fig, ax = plt.subplots(figsize=(8, 4))
sns.lineplot(df,
"Average-Kimura",
"Percentage-of-queries",
hue="Ancestor",
figure_options=FigureOptions(save_fig=next_name(pd_work),
ylabel="Percentage of queries",
xlabel="Average Kimura"),
ax=ax,
show=True,
legend_loc="best",
sns_kwargs={"palette": CM.get_map("ancestor")})
sns.lineplot(df,
"Average-Kimura",
"Cumulative-percentage-of-queries",
hue="Ancestor",
figure_options=FigureOptions(save_fig=next_name(pd_work), ),
sns_kwargs={"palette": CM.get_map("ancestor")})
# standard dev
df = bin_data_one_d(env, df_all[df_all["Support"] > 2], "Std-Kimura",
num_steps)
sns.lineplot(df,
"Std-Kimura",
"Accuracy",
hue="Ancestor",
figure_options=FigureOptions(save_fig=next_name(pd_work), ),
sns_kwargs={"palette": CM.get_map("ancestor")})
sns.lineplot(df,
"Std-Kimura",
"Number-of-queries",
hue="Ancestor",
figure_options=FigureOptions(save_fig=next_name(pd_work), ),
sns_kwargs={"palette": CM.get_map("ancestor")})
total_per_ancestor = {
ancestor: (df["Ancestor"].isin({ancestor})).sum()
for ancestor in ancestors
}
df["Percentage-of-queries"] = 0
df["Cumulative-percentage-of-queries"] = 0
df.reset_index(inplace=True)
for ancestor, df_group in df.groupby(
"Ancestor", as_index=False): # type: str, pd.DataFrame
df_group.sort_values("Std-Kimura", inplace=True)
index = df_group.index
prev = 0
total = df_group["Number-of-queries"].sum()
df.loc[index, "Percentage-of-queries"] = 100 * df.loc[
index, "Number-of-queries"] / float(total)
for i in index:
df.loc[i, "Cumulative-percentage-of-queries"] = prev + df.loc[
i, "Percentage-of-queries"]
prev = df.loc[i, "Cumulative-percentage-of-queries"]
sns.lineplot(df,
"Std-Kimura",
"Percentage-of-queries",
hue="Ancestor",
figure_options=FigureOptions(save_fig=next_name(pd_work), ),
sns_kwargs={"palette": CM.get_map("ancestor")})
sns.lineplot(df,
"Std-Kimura",
"Cumulative-percentage-of-queries",
hue="Ancestor",
figure_options=FigureOptions(save_fig=next_name(pd_work), ),
sns_kwargs={"palette": CM.get_map("ancestor")})
def viz_summary_per_gcfid(env, df, title=None):
# type: (Environment, pd.DataFrame) -> None
pd_work = env['pd-work']
sns.catplot(df,
"Ancestor",
"GMS2=SBSP % SBSP",
kind="box",
figure_options=FigureOptions(
save_fig=next_name(pd_work),
ylim=[None, 100],
title=title,
),
sns_kwargs={"palette": CM.get_map("ancestor")})
sns.catplot(df,
"Ancestor",
"(GMS2=SBSP)!=NCBI % GMS2=SBSP",
kind="box",
figure_options=FigureOptions(save_fig=next_name(pd_work),
ylim=[0, 20],
ylabel="1 - Sen(NCBI, GMS2=SBSP)",
xlabel="Clade",
title=title),
sns_kwargs={"palette": CM.get_map("ancestor")})
# per GC
sns.scatterplot(df,
"Genome GC",
"(GMS2=SBSP)!=NCBI % GMS2=SBSP",
hue="Ancestor",
figure_options=FigureOptions(
save_fig=next_name(pd_work),
ylim=[0, None],
title=title,
),
legend_loc="best",
sns_kwargs={"palette": CM.get_map("ancestor")})
# per GC
sns.lmplot(df,
"Genome GC",
"(GMS2=SBSP)!=NCBI % GMS2=SBSP",
hue="Ancestor",
figure_options=FigureOptions(
save_fig=next_name(pd_work),
ylim=[0, None],
title=title,
ylabel="1 - Sen(NCBI, GMS2=SBSP)",
),
sns_kwargs={
"palette": CM.get_map("ancestor"),
"scatter": False,
"lowess": True
})
sns.lmplot(df,
"Genome GC",
"(GMS2=SBSP)!=NCBI % GMS2=SBSP",
hue="Ancestor",
figure_options=FigureOptions(
save_fig=next_name(pd_work),
ylim=[0, None],
title=title,
ylabel="1 - Sen(NCBI, GMS2=SBSP)",
),
legend_loc="best",
sns_kwargs={
"palette": CM.get_map("ancestor"),
"scatter": True,
"lowess": True,
"scatter_kws": {
"s": 5
},
"aspect": 1.5
})
sns.lmplot(df,
"Genome GC",
"GMS2=SBSP",
hue="Ancestor",
figure_options=FigureOptions(
save_fig=next_name(pd_work),
ylim=[0, None],
title=title,
),
sns_kwargs={
"palette": CM.get_map("ancestor"),
"scatter": True,
"lowess": True,
"scatter_kws": {
"s": 5
}
})
sns.lmplot(df,
"Genome GC",
"GMS2=SBSP % SBSP",
hue="Ancestor",
figure_options=FigureOptions(
save_fig=next_name(pd_work),
ylim=[50, 100],
title=title,
),
sns_kwargs={
"palette": CM.get_map("ancestor"),
"scatter": True,
"lowess": True,
"scatter_kws": {
"s": 5
}
})
sns.lmplot(df,
"Genome GC",
"GMS2=SBSP % GMS2",
hue="Ancestor",
figure_options=FigureOptions(
save_fig=next_name(pd_work),
ylim=[50, 100],
title=title,
),
sns_kwargs={
"palette": CM.get_map("ancestor"),
"scatter": True,
"lowess": True,
"scatter_kws": {
"s": 5
}
})
sns.scatterplot(df,
"NCBI",
"(GMS2=SBSP)!=NCBI % GMS2=SBSP",
hue="Ancestor",
figure_options=FigureOptions(
save_fig=next_name(pd_work),
ylim=[0, None],
title=title,
),
sns_kwargs={
"palette": CM.get_map("ancestor"),
})
sns.scatterplot(df,
"GMS2=SBSP",
"(GMS2=SBSP)!=NCBI % GMS2=SBSP",
hue="Ancestor",
figure_options=FigureOptions(
save_fig=next_name(pd_work),
ylim=[0, None],
title=title,
),
sns_kwargs={
"palette": CM.get_map("ancestor"),
})
# per GC
sns.scatterplot(df,
"Genome GC",
"(GMS2=SBSP)!=Prodigal % GMS2=SBSP",
hue="Ancestor",
figure_options=FigureOptions(
save_fig=next_name(pd_work),
ylim=[0, None],
title=title,
),
sns_kwargs={"palette": CM.get_map("ancestor")})
def viz_summary_per_gcfid_per_step(env, df):
# type: (Environment, pd.DataFrame) -> None
pd_work = env['pd-work']
list_df = list()
for gcfid, df_group in df.groupby("GCFID", as_index=False):
df.loc[df_group.index, "Total SBSP"] = df.loc[df_group.index,
"SBSP"].sum()
df.loc[df_group.index, "Total GMS2"] = df.loc[df_group.index,
"GMS2"].sum()
df.loc[df_group.index, "Total GMS2=SBSP"] = df.loc[df_group.index,
"GMS2=SBSP"].sum()
tag = None
for step in ["A", "B", "C"]:
if tag is None:
tag = step
else:
tag += "+" + step
df_summary_per_gcfid = get_summary_per_gcfid(
df[df["Predicted-at-step"] <= step])
df_summary_per_gcfid["SBSP Step"] = tag
list_df.append(df_summary_per_gcfid)
df_per_gcfid_per_step = pd.concat(list_df, sort=False)
import matplotlib.pyplot as plt
# fig, ax = plt.subplots()
#
# sns.lineplot(df_per_gcfid_per_step, "SBSP Step", "SBSP", hue="GCFID", ax=ax,
# sns_kwargs={"palette": CM.get_map("verified")},
# legend=False
# )
# for l in ax.lines:
# l.set_linestyle("--")
#
# ax2 = ax.twinx()
# sns.lineplot(df_per_gcfid_per_step, "SBSP Step", "Sen(SBSP,NCBI)", hue="GCFID", ax=ax2,
# sns_kwargs={"palette": CM.get_map("verified")},)
#
# fo = FigureOptions(
# xlabel="SBSP Step",
# ylabel="Percentage",
# # ylim=[0, 105],
# save_fig=next_name(env["pd-work"])
# )
# FigureOptions.set_properties_for_axis(ax, fo)
# plt.subplots_adjust(bottom=0.2)
# handles, labels = ax.get_legend_handles_labels()
# ax.legend(handles=handles[1:], labels=labels[1:],
# loc="lower center", ncol=4, bbox_to_anchor=(0.5, -0.25))
#
# plt.savefig(fo.save_fig)
# plt.show()
fig, axes = plt.subplots(3, 2, sharex="all", sharey="row")
ax = axes[:, 0]
sns.lineplot(df_per_gcfid_per_step,
"SBSP Step",
"Sen(SBSP,NCBI)",
hue="GCFID",
ax=ax[0],
sns_kwargs={"palette": CM.get_map("verified")},
legend=False,
figure_options=FigureOptions(
ylabel="Sensitivity",
ylim=[85, 105],
))
sns.lineplot(df_per_gcfid_per_step,
"SBSP Step",
"Cov(SBSP,NCBI)",
hue="GCFID",
ax=ax[1],
sns_kwargs={"palette": CM.get_map("verified")},
legend=False,
figure_options=FigureOptions(ylabel="Percent of Genes",
ylim=[0, None]))
sns.lineplot(df_per_gcfid_per_step,
"SBSP Step",
"SBSP",
hue="GCFID",
ax=ax[2],
sns_kwargs={"palette": CM.get_map("verified")},
legend=False,
figure_options=FigureOptions(ylabel="Number of Genes",
ylim=[0, None]))
fig.align_ylabels(ax)
# plt.savefig(next_name(env["pd-work"]))
# plt.show()
# fig, ax = plt.subplots(3, 1, sharex="all")
ax = axes[:, 1]
sns.lineplot(df_per_gcfid_per_step,
"SBSP Step",
"Sen(GMS2=SBSP,NCBI)",
hue="GCFID",
ax=ax[0],
sns_kwargs={"palette": CM.get_map("verified")},
legend=False,
figure_options=FigureOptions(
ylabel="Sensitivity",
ylim=[85, 105],
))
sns.lineplot(df_per_gcfid_per_step,
"SBSP Step",
"Cov(GMS2=SBSP,NCBI)",
hue="GCFID",
ax=ax[1],
sns_kwargs={"palette": CM.get_map("verified")},
legend=False,
figure_options=FigureOptions(ylabel="Percent of Genes",
ylim=[0, None]))
sns.lineplot(df_per_gcfid_per_step,
"SBSP Step",
"GMS2=SBSP",
hue="GCFID",
ax=ax[2],
sns_kwargs={"palette": CM.get_map("verified")},
figure_options=FigureOptions(ylabel="Number of Genes",
ylim=[0, None]))
ax[2].get_legend().remove()
fig.align_ylabels(ax)
for ax in axes.ravel():
ax.set_xlabel("Steps")
axes[0][0].set_title("SBSP")
axes[0][1].set_title("GMS2=SBSP")
fig.subplots_adjust(bottom=0.21)
# handles, labels = ax.get_legend_handles_labels()
# fig.legend(handles=handles[1:], labels=labels[1:], loc="lower center", ncol=4)#, bbox_to_anchor=(0.5, -0.25))
handles, labels = ax.get_legend_handles_labels()
labels[0] = "Genome"
fig.legend(handles=handles, labels=labels, loc="lower center",
ncol=3) #, bbox_to_anchor=(0.5, -0.25))
plt.savefig(next_name(env["pd-work"]))
plt.show()
# three plots
for gcfid, df_group in df.groupby("GCFID", as_index=False):
df.loc[df_group.index,
"Total SBSP"] = ((df_group["SBSP"]) & (df_group["NCBI"])).sum()
df.loc[df_group.index,
"Total GMS2"] = ((df_group["GMS2"]) & (df_group["NCBI"])).sum()
df.loc[df_group.index, "Total GMS2=SBSP"] = ((df_group["GMS2=SBSP"]) &
(df_group["NCBI"])).sum()
df_all = get_summary_per_gcfid(df)
print(df_all[[
"GCFID", "NCBI", "Sen(SBSP,NCBI)", "Sen(GMS2,NCBI)",
"Sen(GMS2=SBSP,NCBI)"
]].to_string(index=False))
print(df_all[[
"GCFID", "NCBI", "Cov2(SBSP,NCBI)", "Cov2(GMS2,NCBI)",
"Cov2(GMS2=SBSP,NCBI)"
]].to_string(index=False))
import sys
sys.exit()
def viz_per_genome(env, df):
# type: (Environment, pd.DataFrame) -> None
df_grp = df.groupby(["Genome", "Ancestor"], as_index=False).mean()
sns.catplot(df_grp,
"Ancestor",
"BLAST",
figure_options=FigureOptions(save_fig=next_name(
env["pd-work"]),
xlabel="Clade",
ylabel="Number of BLASTp Hits"),
sns_kwargs={"palette": CM.get_map("ancestor")})
# list_grp = list()
# for _, df_grp in df.groupby("Genome", as_index=False):
# indices = df_grp.index
#
# list_grp.append({
# "Genome": df.at[indices[0], "Genome"],
# "Ancestor": df.at[indices[0], "Ancestor"],
# "= 0": len(df_grp[df_grp["BLAST"] == 0]),
# **{
# f"< {x}": len(df_grp[df_grp["BLAST"] < x]) for x in [5, 10, 20, 50, 100, 500, 1000, 5000, 10000]
# },
# "> 10000": len(df_grp[df_grp["BLAST"] > 10000])
# })
#
# df_grp = pd.DataFrame(list_grp)
# sns.catplot(df_grp, "Ancestor", "= 0")
# sns.catplot(df_grp, "Ancestor", "< 5")
# sns.catplot(df_grp, "Ancestor", "< 50")
# sns.catplot(df_grp, "Ancestor", "< 100")
# plots
# 1) x: number of queries with < x targets
# compute per genome, the % of queries with hits <= 0, 5, 10, 20, 40, 80, 160, ... 240 580 1160, ...
# plot
list_entries = list()
for _, df_grp in df.groupby("Genome", as_index=False):
indices = df_grp.index
genome = df.at[indices[0], "Genome"]
ancestor = df.at[indices[0], "Ancestor"]
total_queries = len(df_grp)
curr = 0
for n in range(40):
list_entries.append({
"Genome":
genome,
"Ancestor":
ancestor,
"x":
curr,
"y":
100 * len(df_grp[df_grp["BLAST"] < curr]) / total_queries
})
# if list_entries[-1]["y"] == 100:
# break
if curr == 0:
curr = 5
else:
curr *= 1.2
df_tmp = pd.DataFrame(list_entries)
SMALL_SIZE = 16
MEDIUM_SIZE = 22
BIGGER_SIZE = 24
matplotlib.rcParams.update({
# "pgf.texsystem": "pdflatex",
'font.family': 'serif',
'text.usetex': True,
'pgf.rcfonts': False,
'font.size': SMALL_SIZE, # controls default text sizes
'axes.titlesize': SMALL_SIZE, # fontsize of the axes title
'axes.labelsize': MEDIUM_SIZE, # fontsize of the x and y labels
'xtick.labelsize': SMALL_SIZE, # fontsize of the tick labels
'ytick.labelsize': SMALL_SIZE, # fontsize of the tick labels
'legend.fontsize': 12, # legend fontsize
'figure.titlesize': BIGGER_SIZE, # fontsize of the figure title
})
sns.lineplot(df_tmp,
"x",
"y",
hue="Ancestor",
figure_options=FigureOptions(
xlabel="Number of BLASTp hits",
ylabel="Cumulative percentage of queries (per genome)",
save_fig=next_name(env["pd-work"]),
),
legend_loc="best",
legend_title="",
legend_ncol=2,
sns_kwargs={
"ci": "sd",
"palette": CM.get_map("ancestor")
})
sns.lineplot(df_tmp,
"y",
"x",
hue="Ancestor",
figure_options=FigureOptions(
ylabel="Number of BLASTp hits",
xlabel="Cumulative percentage of queries (per genome)",
save_fig=next_name(env["pd-work"]),
),
legend_loc="best",
legend_title="",
legend_ncol=2,
sns_kwargs={
"ci": "sd",
"palette": CM.get_map("ancestor")
})
SMALL_SIZE = 14
MEDIUM_SIZE = 18
BIGGER_SIZE = 20
matplotlib.rcParams.update({
# "pgf.texsystem": "pdflatex",
'font.family': 'serif',
'text.usetex': True,
'pgf.rcfonts': False,
'font.size': SMALL_SIZE, # controls default text sizes
'axes.titlesize': SMALL_SIZE, # fontsize of the axes title
'axes.labelsize': MEDIUM_SIZE, # fontsize of the x and y labels
'xtick.labelsize': SMALL_SIZE, # fontsize of the tick labels
'ytick.labelsize': SMALL_SIZE, # fontsize of the tick labels
'legend.fontsize': 12, # legend fontsize
'figure.titlesize': BIGGER_SIZE, # fontsize of the figure title
})
fig, axes = plt.subplots(2, 2, sharex="all", sharey="all")
ancestors = sorted(set(df["Ancestor"]))
for anc, ax in zip(ancestors, axes.ravel()):
df_anc = df_tmp[df_tmp["Ancestor"] == anc]
sns.lineplot(df_anc[df_anc["x"] <= 40],
"x",
"y",
hue="Ancestor",
legend=None,
ax=ax,
sns_kwargs={
"ci": "sd",
"palette": CM.get_map("ancestor")
})
ax.set_title(anc)
ax.set_xlabel("")
ax.set_ylabel("")
figure_options = FigureOptions(
xlabel="Number of BLASTp hits",
ylabel="Cumulative percentage of\nqueries (per genome)",
save_fig=next_name(env["pd-work"]),
)
fig.add_subplot(111, frameon=False)
# # hide tick and tick label of the big axes
plt.tick_params(top=False,
bottom=False,
left=False,
right=False,
which="both",
labelbottom=False,
labeltop=False,
labelleft=False,
labelright=False)
plt.xlabel(figure_options.xlabel, labelpad=30)
plt.ylabel(figure_options.ylabel, labelpad=30)
# save_figure(figure_options, fig)
fig.savefig(next_name(env["pd-work"]), bbox_inches="tight")
plt.show()
def viz_summary_per_gcfid_per_step(env, df):
# type: (Environment, pd.DataFrame) -> None
# gather analysis for steps A, A+B, and A+B+C
list_df = list() # type: List[pd.DataFrame]
# compute total number of predictions per tool, per genome
for gcfid, df_group in df.groupby("GCFID", as_index=False):
df.loc[df_group.index, "Total SBSP"] = df.loc[df_group.index,
"SBSP"].sum()
df.loc[df_group.index, "Total GMS2"] = df.loc[df_group.index,
"GMS2"].sum()
df.loc[df_group.index, "Total GMS2=SBSP"] = df.loc[df_group.index,
"GMS2=SBSP"].sum()
# loop over steps A, A+B, and A+B+C and collect stats
tag = None
for step in ["A", "B", "C"]:
if tag is None:
tag = step
else:
tag += "+" + step
df_summary_per_gcfid = get_summary_per_gcfid(
df[df["Predicted-at-step"] <= step])
df_summary_per_gcfid["SBSP Step"] = tag
list_df.append(df_summary_per_gcfid)
df_per_gcfid_per_step = pd.concat(list_df, sort=False)
import matplotlib.pyplot as plt
# fig, ax = plt.subplots()
#
# sns.lineplot(df_per_gcfid_per_step, "SBSP Step", "SBSP", hue="GCFID", ax=ax,
# sns_kwargs={"palette": CM.get_map("verified")},
# legend=False
# )
# for l in ax.lines:
# l.set_linestyle("--")
#
# ax2 = ax.twinx()
# sns.lineplot(df_per_gcfid_per_step, "SBSP Step", "Sen(SBSP,NCBI)", hue="GCFID", ax=ax2,
# sns_kwargs={"palette": CM.get_map("verified")},)
#
# fo = FigureOptions(
# xlabel="SBSP Step",
# ylabel="Percentage",
# # ylim=[0, 105],
# save_fig=next_name(env["pd-work"])
# )
# FigureOptions.set_properties_for_axis(ax, fo)
# plt.subplots_adjust(bottom=0.2)
# handles, labels = ax.get_legend_handles_labels()
# ax.legend(handles=handles[1:], labels=labels[1:],
# loc="lower center", ncol=4, bbox_to_anchor=(0.5, -0.25))
#
# plt.savefig(fo.save_fig)
# plt.show()
fig, axes = plt.subplots(3, 2, sharex="all", sharey="row")
ax = axes[:, 0]
sns.lineplot(df_per_gcfid_per_step,
"SBSP Step",
"Sen(SBSP,NCBI)",
hue="GCFID",
ax=ax[0],
sns_kwargs={"palette": CM.get_map("verified")},
legend=False,
figure_options=FigureOptions(
ylabel="Error rate (\%)",
ylim=[0, 20],
))
sns.lineplot(df_per_gcfid_per_step,
"SBSP Step",
"Cov(SBSP,NCBI)",
hue="GCFID",
ax=ax[1],
sns_kwargs={"palette": CM.get_map("verified")},
legend=False,
figure_options=FigureOptions(ylabel="Percentage\nof Genes",
ylim=[0, None]))
sns.lineplot(df_per_gcfid_per_step,
"SBSP Step",
"SBSP",
hue="GCFID",
ax=ax[2],
sns_kwargs={"palette": CM.get_map("verified")},
legend=False,
figure_options=FigureOptions(ylabel="Number\nof Genes",
ylim=[0, None]))
fig.align_ylabels(ax)
# plt.savefig(next_name(env["pd-work"]))
# plt.show()
# fig, ax = plt.subplots(3, 1, sharex="all")
ax = axes[:, 1]
sns.lineplot(df_per_gcfid_per_step,
"SBSP Step",
"Sen(GMS2=SBSP,NCBI)",
hue="GCFID",
ax=ax[0],
sns_kwargs={"palette": CM.get_map("verified")},
legend=False,
figure_options=FigureOptions(
ylabel="Error",
ylim=[0, None],
))
sns.lineplot(df_per_gcfid_per_step,
"SBSP Step",
"Cov(GMS2=SBSP,NCBI)",
hue="GCFID",
ax=ax[1],
sns_kwargs={"palette": CM.get_map("verified")},
legend=False,
figure_options=FigureOptions(ylabel="Percentage of Genes",
ylim=[0, None]))
sns.lineplot(df_per_gcfid_per_step,
"SBSP Step",
"GMS2=SBSP",
hue="GCFID",
ax=ax[2],
sns_kwargs={"palette": CM.get_map("verified")},
figure_options=FigureOptions(ylabel="Number of Genes",
ylim=[0, None]))
ax[2].get_legend().remove()
fig.align_ylabels(ax)
for ax in axes.ravel():
ax.set_xlabel("Steps")
axes[0][0].set_title(TOOL)
axes[0][1].set_title(TOOLp)
fig.subplots_adjust(bottom=0.21)
# handles, labels = ax.get_legend_handles_labels()
# fig.legend(handles=handles[1:], labels=labels[1:], loc="lower center", ncol=4)#, bbox_to_anchor=(0.5, -0.25))
handles, labels = ax.get_legend_handles_labels()
labels[0] = "Genome"
fig.legend(handles=handles, labels=labels, loc="lower center",
ncol=3) #, bbox_to_anchor=(0.5, -0.25))
plt.savefig(next_name(env["pd-work"]))
plt.show()
# three plots
for gcfid, df_group in df.groupby("GCFID", as_index=False):
df.loc[df_group.index,
"Total SBSP"] = ((df_group["SBSP"]) & (df_group["NCBI"])).sum()
df.loc[df_group.index,
"Total GMS2"] = ((df_group["GMS2"]) & (df_group["NCBI"])).sum()
df.loc[df_group.index, "Total GMS2=SBSP"] = ((df_group["GMS2=SBSP"]) &
(df_group["NCBI"])).sum()
df_all = get_summary_per_gcfid(df)
# map column names for tables
columns = [
"GCFID", "NCBI", "Sen(SBSP,NCBI)", "Sen(GMS2,NCBI)",
"Sen(GMS2=SBSP,NCBI)", "Cov2(SBSP,NCBI)", "Cov2(GMS2,NCBI)",
"Cov2(GMS2=SBSP,NCBI)"
]
df_sen = df_all.copy()[columns].rename(columns={
"GCFID": "Genome",
"NCBI": "Verified",
"Sen(SBSP,NCBI)": "SBSP",
"Sen(GMS2,NCBI)": "GMS2",
"Sen(GMS2=SBSP,NCBI)": "GMS2=SBSP",
},
inplace=False)
df_sen[["Genome", "Verified", "SBSP", "GMS2",
"GMS2=SBSP"]].to_csv(os_join(env["pd-work"], "sensitivity.csv"),
index=False)
# print(df_all[["GCFID", "NCBI", "Cov2(SBSP,NCBI)", "Cov2(GMS2,NCBI)", "Cov2(GMS2=SBSP,NCBI)"]].to_string(index=False))
df_cov = df_all[columns].rename(columns={
"GCFID": "Genome",
"NCBI": "Verified",
"Cov2(SBSP,NCBI)": "SBSP",
"Cov2(GMS2,NCBI)": "GMS2",
"Cov2(GMS2=SBSP,NCBI)": "GMS2=SBSP",
},
inplace=False)
df_cov[["Genome", "Verified", "SBSP", "GMS2",
"GMS2=SBSP"]].to_csv(os_join(env["pd-work"], "coverage.csv"),
index=False)
def main(env, args):
# type: (Environment, argparse.Namespace) -> None
df = pd.read_csv(args.pf_data)
df["chunk-size"] /= 1000
import matplotlib.pyplot as plt
fig, ax = plt.subplots()
sns.lineplot(df[df["Tool"] == "SBSP"], "chunk-size", "percentage-common-3prime-and-5prime-from-common-3prime",
hue="Genome",
sns_kwargs={"palette": CM.get_map("verified"), "linestyle": "dashed"},
ax=ax,
legend=False,
figure_options=FigureOptions(
xlabel="Chunk size (mb)",
ylabel="Accuracy",
ylim=[74, 101],
save_fig=next_name(env["pd-work"])
))
for l in ax.lines:
l.set_linestyle("--")
sns.lineplot(df[df["Tool"] == "GMS2"], "chunk-size", "percentage-common-3prime-and-5prime-from-common-3prime",
hue="Genome",
sns_kwargs={"palette": CM.get_map("verified")},
legend_loc="best",
legend_ncol=2,
ax=ax)
if args.with_mgm:
y_max = ax.get_ylim()[1]
ax.axvline(50, 0, y_max, color="grey", linestyle="dashed")
ax.axhline(74, 5, 49, color="grey", linestyle="dashed")
ax.annotate("MGM", (5, 72))
if "MGM" in set(df["Tool"]):
sns.lineplot(df[df["Tool"] == "MGM"], "chunk-size", "percentage-common-3prime-and-5prime-from-common-3prime",
hue="Genome",
sns_kwargs={"palette": CM.get_map("verified"), "linestyle": "-."},
ax=ax,
legend=False)
for l in ax.lines[len(ax.lines)-5:]:
l.set_linestyle(":")
fo = FigureOptions(
xlabel="Chunk size (mb)",
ylabel="Accuracy",
ylim=[74,101],
save_fig=next_name(env["pd-work"])
)
FigureOptions.set_properties_for_axis(ax, fo)
plt.savefig(fo.save_fig)
plt.show()
def analyze_independent_predictions(max_candidates, sen_a, sen_b):
# type: (int, float, float) -> None
sensitivities = {
"Random": sensitivity_random,
"Independent": sensitivity_independent,
"Fully dependent": sensitivity_fully_dependent
}
agree_given_pred = {
"Random": agree_given_pred_random,
"Independent": agree_given_pred_independent,
"Fully dependent": agree_given_pred_fully_dependent
}
df = compute_data(sensitivities, agree_given_pred, max_candidates)
plot_sensitivities_vs_num_candidates(sensitivities, max_candidates, sen_a,
sen_b)
sns.lineplot(
df[(df["Sensitivity A"] == 0.9) & (df["Sensitivity B"] == 0.9)],
"Number of candidates",
"Probability",
hue="Condition",
sns_kwargs={"palette": CM.get_map("independence-conditions")},
legend_loc="best",
figure_options=FigureOptions(
save_fig=next_name("."),
ylabel=r"$P(y=s|x_1=y, x_2=y)$",
# xlim=[None, 40]
))
# error
df["1 - Probability"] = 1 - df["Probability"]
sns.lineplot(
df[(df["Sensitivity A"] == 0.9) & (df["Sensitivity B"] == 0.9)],
"Number of candidates",
"1 - Probability",
hue="Condition",
sns_kwargs={"palette": CM.get_map("independence-conditions")},
legend_loc="best",
figure_options=FigureOptions(
save_fig=next_name("."),
ylabel=r"$P(y\neq s|x_1=y, x_2=y)$",
# xlim=[None, 40]
))
import matplotlib.pyplot as plt
fig, axes = plt.subplots(1, 2, sharey="all", figsize=(10, 4))
sns.lineplot(df[(df["Sensitivity A"] == 0.9)
& (df["Sensitivity B"] == 0.9)],
"Number of candidates",
"Probability",
hue="Condition",
sns_kwargs={"palette": CM.get_map("independence-conditions")},
ax=axes[0],
legend=False,
figure_options=FigureOptions(title="Sensitivity = 0.9", ))
sns.lineplot(df[(df["Sensitivity A"] == df["Sensitivity B"])
& (df["Number of candidates"] == 25)],
"Sensitivity A",
"Probability",
hue="Condition",
ax=axes[1],
sns_kwargs={"palette": CM.get_map("independence-conditions")},
figure_options=FigureOptions(
ylim=[0, 1.05],
xlim=[0, 1],
xlabel="Sensitivity",
title="Number of candidates = 25",
))
save_figure(FigureOptions(save_fig=next_name(".")), fig)
plt.show()
df_tmp = df[(df["Sensitivity A"] == df["Sensitivity B"])
& (df["Condition"] == "Independent") &
(df["Sensitivity A"].isin(
{0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9}))]
df_tmp.rename(columns={"Sensitivity A": "Sensitivity"}, inplace=True)
sns.lineplot(
df_tmp,
"Number of candidates",
"Probability",
hue="Sensitivity",
figure_options=FigureOptions(
# ylim=[0, 1.05],
# xlim=[0, 1],
title="Independent algorithms",
save_fig=next_name(".")),
)
# for condition in set(df["Condition"]):
#
# sns.kdeplot(
# df[(df["Condition"] == condition) & (df["Sensitivity A"] == df["Sensitivity B"])],
# "Sensitivity A", "Number of candidates", "Probability",
# figure_options=FigureOptions(
# title=condition
# ))
import matplotlib.pyplot as plt
fig, axes = plt.subplots(1, 2, sharey="all", figsize=(10, 4))
sns.lineplot(df[(df["Sensitivity A"] == 0.9)
& (df["Sensitivity B"] == 0.9)],
"Number of candidates",
"Agree given prediction",
hue="Condition",
sns_kwargs={"palette": CM.get_map("independence-conditions")},
ax=axes[0],
legend=False,
figure_options=FigureOptions(title="Sensitivity = 0.9", ))
sns.lineplot(df[(df["Sensitivity A"] == df["Sensitivity B"])
& (df["Number of candidates"] == 25)],
"Sensitivity A",
"Agree given prediction",
hue="Condition",
ax=axes[1],
sns_kwargs={"palette": CM.get_map("independence-conditions")},
figure_options=FigureOptions(
ylim=[0, 1.05],
xlim=[0, 1],
xlabel="Sensitivity",
title="Number of targets = 25",
))
save_figure(FigureOptions(save_fig=next_name(".")), fig)
plt.show()
def plot_candidate_stops(env, df):
# type: (Environment, pd.DataFrame) -> None
from sbsp_viz.colormap import ColorMap as CM
plot_candidate_codons(env, df, ["TAA", "TAG", "TGA"], CM.get_map("stops"))