Spaces:
Build error
Build error
File size: 3,865 Bytes
d5ff673 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 |
"""Plot pandas.DataFrame with DBSCAN clustering."""
# pylint: disable=invalid-name, too-many-arguments
import numpy as np
import pandas as pd
import matplotlib
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.cluster import DBSCAN
from fastlid import fastlid
import logzero
from logzero import logger
from radiobee.cmat2tset import cmat2tset
# turn interactive when in ipython session
_ = """
if "get_ipython" in globals():
plt.ion()
else:
plt.switch_backend("Agg")
# """
logzero.loglevel(20) # 10: debug on
fastlid.set_languages = ["en", "zh"]
# fmt: off
def plot_cmat(
# df_: pd.DataFrame,
cmat: np.ndarray,
eps: float = 10,
min_samples: int = 6,
# ylim: int = None,
xlabel: str = "zh",
ylabel: str = "en",
backend: str = "Agg",
showfig: bool = False,
):
# ) -> plt:
# fmt: on
"""Plot df with DBSCAN clustering.
Args:
df_: pandas.DataFrame, with three columns columns=["x", "y", "cos"]
Returns:
matplotlib.pyplot: for possible use in gradio
plot_df(pd.DataFrame(cmat2tset(smat), columns=['x', 'y', 'cos']))
df_ = pd.DataFrame(cmat2tset(smat), columns=['x', 'y', 'cos'])
# sort 'x', axis 0 changes, index regenerated
df_s = df_.sort_values('x', axis=0, ignore_index=True)
# sorintg does not seem to impact clustering
DBSCAN(1.5, min_samples=3).fit(df_).labels_
DBSCAN(1.5, min_samples=3).fit(df_s).labels_
"""
logger.debug(
'"get_ipython" in globals(): %s', "get_ipython" in globals()
)
len1, len2 = cmat.shape
df_ = pd.DataFrame(cmat2tset(cmat))
df_.columns = ["x", "y", "cos"]
backend_saved = matplotlib.get_backend()
# switch backend if necessary
if backend_saved != backend:
plt.switch_backend(backend)
# len1 = len(lst1) # noqa
# len2 = len(lst2) # noqa
# lang1, _ = fastlid(" ".join(lst1))
# lang2, _ = fastlid(" ".join(lst2))
# xlabel: str = lang1
# ylabel: str = lang2
sns.set()
sns.set_style("darkgrid")
# close all existing figures, necesssary for hf spaces
plt.close("all")
# if sys.platform not in ["win32", "linux"]:
# plt.switch_backend('Agg') # to cater for Mac, thanks to WhiteFox
fig = plt.figure()
gs = fig.add_gridspec(2, 2, wspace=0.4, hspace=0.58)
ax2 = fig.add_subplot(gs[0, 0])
ax0 = fig.add_subplot(gs[0, 1])
ax1 = fig.add_subplot(gs[1, 0])
cmap = "viridis_r"
sns.heatmap(cmat, cmap=cmap, ax=ax2).invert_yaxis()
ax2.set_xlabel(xlabel)
ax2.set_ylabel(ylabel)
ax2.set_title("cos similarity heatmap")
fig.suptitle("alignment projection")
_ = DBSCAN(min_samples=min_samples, eps=eps).fit(df_).labels_ > -1
# _x = DBSCAN(min_samples=min_samples, eps=eps).fit(df_).labels_ < 0
_x = ~_
df_.plot.scatter("x", "y", c="cos", cmap=cmap, ax=ax0)
# clustered
df_[_].plot.scatter("x", "y", c="cos", cmap=cmap, ax=ax1)
# outliers
df_[_x].plot.scatter("x", "y", c="r", marker="x", alpha=0.6, ax=ax0)
ax0.set_xlabel(xlabel)
ax0.set_ylabel(ylabel)
ax0.set_xlim(0, len1)
ax0.set_ylim(0, len2)
ax0.set_title("max along columns ('x': outliers)")
# ax1.set_xlabel("en")
# ax1.set_ylabel("zh")
ax1.set_xlabel(xlabel)
ax1.set_ylabel(ylabel)
ax1.set_xlim(0, len1)
ax1.set_ylim(0, len2)
ax1.set_title(f"potential aligned pairs ({round(sum(_) / len1, 2):.0%})")
logger.debug(" matplotlib.get_backend(): %s", matplotlib.get_backend())
# if matplotlib.get_backend() not in ["Agg"]:
if showfig:
# plt.ioff() # or we'll just see the plot show and disappear
# plt.show()
plt.show(block=True)
# restore if necessary
if backend_saved != backend:
plt.switch_backend(backend_saved)
# return plt
|