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 catplot(df, x, y, hue=None, kind="box", figure_options=None, **kwargs):
# type: (pd.DataFrame, str, str, str, Union[str, None], FigureOptions, Dict[str, Any]) -> None
sns_kwargs = get_value(kwargs, "sns_kwargs", dict())
g = sns.catplot(x=x, y=y, data=df, kind=kind, hue=hue, legend=False, aspect=1.5, **sns_kwargs)
if kind == "point":
plt.setp(g.ax.lines, linewidth=1) # set lw for all lines of g axes
# plt.setp(g.ax.lines, markersize=0) # set lw for all lines of g axes
#
# if fontsize:
# g.set_xlabels(x, fontsize=fontsize)
# g.set_ylabels(x, fontsize=fontsize)
FigureOptions.set_properties_for_axis(g.axes[0][0], figure_options)
legend = get_value(kwargs, "legend", "full")
legend_loc = get_value(kwargs, "legend_loc", None)
if hue is not None and legend:
title = get_value(kwargs, "legend_title", None)
if not legend_loc:
plt.legend(loc='center left', bbox_to_anchor=(1.05, 0.5), title=title)
else:
plt.legend(loc=legend_loc)
# plt.savefig(next_name(pd_work))
save_figure(figure_options)
plt.show()
def scatterplot(df, x, y, hue=None, figure_options=None, **kwargs):
# type: (pd.DataFrame, str, str, Union[str, None], FigureOptions, Dict[str, Any]) -> None
sns_kwargs = get_value(kwargs, "sns_kwargs", dict())
ax = get_value(kwargs, "ax", None)
identity = get_value(kwargs, "identity", False)
if not ax:
_, ax = plt.subplots()
g = sns.scatterplot(x=x, y=y, hue=hue, data=df, linewidth=0, **sns_kwargs)
if identity:
add_identity(ax, color="r", ls="--")
FigureOptions.set_properties_for_axis(ax, figure_options)
legend = get_value(kwargs, "legend", "full")
legend_loc = get_value(kwargs, "legend_loc", None)
if hue is not None and legend:
title = get_value(kwargs, "legend_title", None)
if not legend_loc:
plt.legend(loc='center left', bbox_to_anchor=(1.05, 0.5), title=title)
else:
plt.legend(loc=legend_loc)
save_figure(figure_options)
plt.show()
def tsplot(df, x, y, hue=None, figure_options=None, **kwargs):
_, ax = plt.subplots()
sns_kwargs = get_value(kwargs, "sns_kwargs", dict())
# g = sns.lmplot(x=x, y=y, hue=hue, data=df, aspect=2, legend=False, ci=None)
sns.tsplot(df[y].values, df[x].values, **sns_kwargs)
if hue is not None:
plt.legend(loc='center left', bbox_to_anchor=(1.05, 0.5))
# FigureOptions.set_properties_for_axis(g.axes[0][0], figure_options)
save_figure(figure_options)
plt.show()
def distplot(df, x, figure_options=None, **kwargs):
_, ax = plt.subplots()
sns_kwargs = get_value(kwargs, "sns_kwargs", dict())
if "kde" not in sns_kwargs:
sns_kwargs["kde"] = True
g = sns.distplot(df[x], bins=50, **sns_kwargs)
FigureOptions.set_properties_for_axis(g.axes, figure_options)
save_figure(figure_options)
plt.show()
def barplot(df, x, y, hue, figure_options=None, **kwargs):
sns_kwargs = get_value(kwargs, "sns_kwargs", dict())
ax = get_value(kwargs, "ax", None)
g = sns.barplot(x=x, y=y, data=df, hue=hue, ax=ax, **sns_kwargs)
if hue is not None:
plt.legend(loc='center left', bbox_to_anchor=(1.05, 0.5))
FigureOptions.set_properties_for_axis(g, figure_options)
plt.tight_layout()
save_figure(figure_options)
# plt.tight_layout(rect=[-0.3,0,1,1.2])
plt.show()
def kdeplot(df, x, y, hue=None, figure_options=None, **kwargs):
# type: (pd.DataFrame, str, str, Union[str, None], FigureOptions, Dict[str, Any]) -> None
sns_kwargs = get_value(kwargs, "sns_kwargs", dict())
_, ax = plt.subplots()
y_df = None if y is None else df[y]
g = sns.kdeplot(df[x], y_df, legend=False, **sns_kwargs)
if hue is not None:
plt.legend(loc='center left', bbox_to_anchor=(1.05, 0.5))
FigureOptions.set_properties_for_axis(ax, figure_options)
save_figure(figure_options)
plt.show()
def contour_kimura_per_ancestor(env, df):
import seaborn
import matplotlib.pyplot as plt
ancestors = sorted(list(set(df["Ancestor"])))
fig, axes = plt.subplots(2,
math.ceil(len(ancestors) / 2),
sharex=True,
sharey=True,
figsize=(6, 6))
for anc, ax in zip(ancestors, axes.ravel()):
df_group = df[df["Ancestor"] == anc]
seaborn.kdeplot(df_group["Min-Kimura"].values,
df_group["Max-Kimura"].values,
ax=ax)
ax.set_title(anc)
# ax.set_ylim([0.45, 0.525])
# fig.xlabel("Min-Kimura")
# plt.xlabel("Min-Kimura")
# plt.ylabel("Max-Kimura")
# fig.text(0.5, 0.04, 'Min-Kimura', ha='center')
# fig.text(0.04, 0.5, 'Max-Kimura', va='center', rotation='vertical')
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("Minimum Kimura", labelpad=20)
plt.ylabel("Maximum Kimura", labelpad=30)
fig.tight_layout()
save_figure(FigureOptions(save_fig=next_name(env["pd-work"])))
plt.show()
def lmplot(df, x, y, hue=None, figure_options=None, **kwargs):
# type: (pd.DataFrame, str, str, Union[str, None], FigureOptions, Dict[str, Any]) -> None
sns_kwargs = get_value(kwargs, "sns_kwargs", dict())
if "aspect" not in sns_kwargs:
sns_kwargs["aspect"] = 2
g = sns.lmplot(x=x, y=y, hue=hue, data=df, legend=False, **sns_kwargs)
FigureOptions.set_properties_for_axis(g.axes[0][0], figure_options)
legend = get_value(kwargs, "legend", "full")
legend_loc = get_value(kwargs, "legend_loc", None)
if hue is not None and legend:
title = get_value(kwargs, "legend_title", None)
if not legend_loc:
g.axes[0][0].legend(loc='center left', bbox_to_anchor=(1.05, 0.5), title=title)
else:
g.axes[0][0].legend(loc=legend_loc)
save_figure(figure_options, fig=g.fig)
plt.subplots_adjust(right=1)
plt.show()
return g
def lineplot(df, x, y, hue=None, figure_options=None, **kwargs):
# type: (pd.DataFrame, str, str, Union[str, None], FigureOptions, Dict[str, Any]) -> None
sns_kwargs = get_value(kwargs, "sns_kwargs", dict())
ax = get_value(kwargs, "ax", None)
show = get_value(kwargs, "show", ax is None)
legend = get_value(kwargs, "legend", "full")
legend_loc = get_value(kwargs, "legend_loc", None)
legend_ncol = get_value(kwargs, "legend_ncol", 1)
identity = get_value(kwargs, "identity", False)
if not ax:
fig, ax = plt.subplots()
else:
fig = ax.get_figure()
g = sns.lineplot(x=x, y=y, hue=hue, data=df, ax=ax, legend=legend, **sns_kwargs)
if identity:
add_identity(ax, color="r", ls="--")
FigureOptions.set_properties_for_axis(ax, figure_options)
if hue is not None and legend:
title = get_value(kwargs, "legend_title", None)
if not legend_loc:
plt.legend(loc='center left', bbox_to_anchor=(1.05, 0.5), title=title, ncol=legend_ncol)
else:
plt.legend(loc=legend_loc, ncol=legend_ncol, title=title)
if title is not None and len(title) == 0:
handles, labels = ax.get_legend_handles_labels()
ax.legend(handles=handles[1:], labels=labels[1:], ncol=legend_ncol)
if show:
save_figure(figure_options, fig)
plt.show()
def plot_per_tool_by_genome_type(env, df):
# type: (Environment, pd.DataFrame) -> None
list_tags = get_tags_for_5prime(df)
num_tags = len(list_tags)
fig, ax = plt.subplots(2,
math.ceil(num_tags / 2),
sharey="all",
sharex="all")
fig.add_axes([.91, .3, .03, .4])
cbar_ax = fig.axes[-1]
#
# save_figure(FigureOptions(
# save_fig=next_name(env["pd-work"])
# ), fig)
#
# plt.show()
# return
import numpy as np
kws = {
# "levels": np.arange(0, 1, 0.2),
# "vmin": 0, "vmax": 0.55,
# "norm": True
"xlim": [0.2, 0.8],
"ylim": [0, 35],
"cbar_max": 1,
"num_steps": 35,
}
cbar_enable = {
"cbar_ax": cbar_ax,
"cbar": True,
}
counter = 0
for tag, c, a in zip(list_tags, ["b", "g", "r", "o"], ax.ravel()):
x, y, y_l, y_u = loess_with_stde(
df, "GC", f"M:{tag}", a, tag.replace("=", ","), **kws,
**cbar_enable if counter == 0 else dict())
a.set_title(
tag.replace("=",
",").replace("NCBI",
"PGAP").replace("GMS2", "GeneMarkS-2"))
a.set_ylabel("")
a.set_xlabel("")
# a.set_ylim([65,100])
# a.set_ylim([0, 35])
# eps_x = [z for z in a.get_ylim()]
# eps_x[0] -= 0.01
# eps_x[1] += 0.01
#
# a.set_xlim(eps_x)
# if counter % 2 == 0:
# a.set_ylabel("Percentage of gene-start differences")
# if counter >= math.ceil(num_tags/2):
# a.set_xlabel("GC")
counter += 1
mappable = a.collections[0]
# plt.legend(loc="best")
figure_options = FigureOptions(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("GC", labelpad=30)
plt.ylabel("Percentage of gene-start differences", labelpad=30)
# plt.xlabel("GC")
# plt.ylabel("Percent 5' Match")
# mappable=create_mappable_for_colorbar(np.arange(0, 0.4, 0.05), "Reds")
# plt.colorbar(mappable, cax=cbar_ax, cmap="Reds")
fig.tight_layout(rect=[-0.02, -0.02, .9, 1])
# plt.tight_layout()
# FigureOptions.set_properties_for_axis(ax, figure_options)
save_figure(figure_options, fig)
plt.show()
#
# for tag in list_tags:
# sns.jointplot(df, "GC", f"M:{tag}")
#
#
# x = df["GC"].values
# y = df[f"M:{list_tags[0]}"].values
# order = np.argsort(x)
# # run it
# y_sm, y_std = lowess(x, y, f=1. / 5.)
# # plot it
# plt.plot(x[order], y_sm[order], color='tomato', label='LOWESS')
# plt.fill_between(x[order], y_sm[order] - 1.96 * y_std[order],
# y_sm[order] + 1.96 * y_std[order], alpha=0.3, label='LOWESS uncertainty')
# # plt.plot(x, y, 'k.', label='Observations')
# # plt.legend(loc='best')
# # run it
# y_sm, y_std = lowess(x, y, f=1. / 5.)
# # plot it
# plt.plot(x[order], y_sm[order], color='tomato', label='LOWESS')
# plt.fill_between(x[order], y_sm[order] - y_std[order],
# y_sm[order] + y_std[order], alpha=0.3, label='LOWESS uncertainty')
# # plt.plot(x, y, 'k.', label='Observations')
# plt.legend(loc='best')
# plt.show()
# calculate a 60 day rolling mean and plot
# calculate a 60 day rolling mean and plot
# df_stacked = stack_columns_as_rows(
# df, [f"M:{tag}" for tag in list_tags], "Percent 5p Match", [f"M:{tag}" for tag in list_tags], "Tools"
# )
#
#
# sns.lmplot(
# df_stacked, "GC", "Percent 5p Match", hue="Tools",
# figure_options=FigureOptions(
# xlabel="Genome GC",
# ylim=[70, 100]
# ),
# legend_loc="best",
# sns_kwargs={"scatter_kws": {"s": 5, "alpha": 0.3}, "lowess": False, "scatter": False, "aspect": 1.5}
# )
# # sns.tsplot(df_stacked, "GC", "Percent 5p Match", hue="Tools", sns_kwargs={"ci":"sd"})
# fig, ax = plt.subplots(1, 1)
# seaborn.lineplot(df["GC"], df[f"M:{list_tags[0]}"])
# # seaborn.tsplot(df, "GC", f"M:{list_tags[0]}" , ci="sd")
# plt.show()
plt.show()
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 heat_map_Kimura_accuracy(env, df_all, x, y, num_steps=20, balance=False):
# type: (Environment, pd.DataFrame, str, str, int) -> None
import matplotlib.pyplot as plt
ancestors = sorted(list(set(df_all["Ancestor"])))
fig, axes = plt.subplots(2,
math.ceil(len(ancestors) / 2),
sharex=True,
sharey=True)
cbar_ax = fig.add_axes([.91, .3, .03, .4])
# fig = plt.figure()
num_rows = 2
num_cols = math.ceil(len(ancestors) / 2)
axis_idx = 0
curr_row = 0
curr_col = 0
for ancestor, df in df_all.groupby("Ancestor", as_index=False):
ax = axes.ravel()[axis_idx]
# ax = plt.subplot2grid((num_rows, num_cols), (curr_row, curr_col))
axis_idx += 1
curr_col += 1
if curr_col == math.ceil(len(ancestors) / 2):
curr_row += 1
curr_col = 0
min_x = min(df[x])
max_x = max(df[x]) + 0.000000001
min_y = min(df[y])
max_y = max(df[y]) + 0.000000001
if balance:
min_x = min_y = min(min_x, min_y)
max_x = max_y = max(max_x, max_y)
ss_x = (max_x - min_x) / float(num_steps)
ss_y = (max_y - min_y) / float(num_steps)
num_col = num_steps
num_row = num_steps
import numpy as np
gms2_eq_sbsp_and_ncbi = np.zeros([num_row, num_col], dtype=float)
gms2_eq_sbsp_eq_ncbi = np.zeros([num_row, num_col], 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, x]
y_val = df.at[index, y]
x_pos = int((x_val - min_x) / ss_x)
y_pos = int((y_val - min_y) / ss_y)
gms2_eq_sbsp_and_ncbi[x_pos][y_pos] += 1 if df.at[
index, "GMS2=SBSP"] and df.at[index, "NCBI"] else 0
gms2_eq_sbsp_eq_ncbi[x_pos][y_pos] += 1 if df.at[
index, "GMS2=SBSP=NCBI"] else 0
gms2_eq_sbsp_and_ncbi[gms2_eq_sbsp_and_ncbi < 10] = 0
accuracy = np.divide(gms2_eq_sbsp_eq_ncbi, gms2_eq_sbsp_and_ncbi)
# accuracy = np.flip(accuracy, 0)
import seaborn
import matplotlib.pyplot as plt
xticks = list(range(0, num_steps, int(num_steps / 5)))
yticks = list(range(0, num_steps, int(num_steps / 5)))
l_x = np.arange(min_x, max_x, ss_x)
l_y = np.arange(min_y, max_y, ss_y)
xticklabels = [round(l_x[i], 2) for i in xticks]
yticklabels = [round(l_y[i], 2) for i in yticks]
g = seaborn.heatmap(accuracy.transpose(),
vmin=0,
vmax=1,
xticklabels=xticklabels,
yticklabels=yticklabels,
ax=ax,
cbar=False)
# cbar_ax=None if axis_idx != 0 else cbar_ax, cbar=axis_idx==0)
# cbar=g.cbar
g.invert_yaxis()
g.set_xticks(xticks)
g.set_yticks(yticks)
g.set_xticklabels(xticklabels, rotation=0)
# g.set_xlabel("Min Kimura")
# g.set_ylabel("Max Kimura")
g.set_title(ancestor)
mappable = ax.collections[0]
# im = plt.gca().get_children()[0]
# cax = fig.add_axes([0.8, 0.1, 0.03, 0.8])
cbar_ax = fig.axes[-1]
# fig.tight_layout(rect=[0, 0, .9, 1])
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(x, labelpad=20)
plt.ylabel(y, labelpad=30)
# ax3 = plt.subplot2grid((num_rows, num_cols), (0, num_cols - 1), rowspan=num_rows,
# )
plt.colorbar(mappable, cax=cbar_ax)
fig.tight_layout(rect=[0, 0, .9, 1])
save_figure(FigureOptions(save_fig=next_name(env["pd-work"])))
plt.show()
def visualize_matrix_column(env, df, col):
# type: (Environment, pd.DataFrame, str) -> None
# first, remove all NA for column
df = df[~df[col].isna()] # we only need non-NA
fp = FontProperties()
fp.set_family("monospace")
# create N x 6 x 4 matrix for RBS
mat = create_numpy_for_column(df, col)
mat = mat.reshape((mat.shape[0], mat.shape[1] * mat.shape[2]))
# get interesting features to view data by
gc = df["GC"]
group = df["GENOME_TYPE"]
for r in range(1):
reducer = umap.UMAP(random_state=r)
reducer = reducer.fit(mat)
embedding = reducer.embedding_
print(embedding.shape)
# fig, ax = plt.subplots()
#
# plt.scatter(embedding[:, 0], embedding[:, 1], c=gc, marker="+")
# plt.colorbar()
# plt.show()
# themes = ["fire", "viridis", "inferno", "blue", "red", "green", "darkblue", "darkred", "darkgreen"]
# fig, axes = plt.subplots(3, 3)
# for ax, theme in zip(axes.ravel(), themes):
# fig, ax = plt.subplots()
# umap.plot.points(reducer, values=gc, theme=theme, )
# plt.show()
ax = umap.plot.points(reducer, values=gc, cmap="viridis")
mappable = create_mappable_for_colorbar(gc, "viridis")
plt.colorbar(mappable)
plt.title(col)
plt.tight_layout()
save_figure(FigureOptions(save_fig=next_name(env["pd-work"])))
plt.show()
umap.plot.points(reducer, labels=group.values, color_key_cmap="Paired")
plt.title(col)
plt.tight_layout()
save_figure(FigureOptions(save_fig=next_name(env["pd-work"])))
plt.show()
# umap.plot.points(reducer, labels=group.values, color_key_cmap="Dark2")
# plt.title(col)
# save_figure(FigureOptions(
# save_fig=next_name(env["pd-work"])
# ))
# plt.show()
umap.plot.points(reducer, labels=df["Type"])
plt.title(col)
plt.tight_layout()
save_figure(FigureOptions(save_fig=next_name(env["pd-work"])))
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()
