adaptation_specialization_material/plots/word2vec_validation.py

import numpy as np
from matplotlib import pyplot as plt
import matplotlib
matplotlib.use("pgf")
matplotlib.rcParams.update(
    {
        "pgf.texsystem": "xelatex",
        "font.family": "serif",
        "font.serif": "Times New Roman",
        "text.usetex": True,
        "pgf.rcfonts": False,
    }
)
plt.rcParams["text.latex.preamble"].join([
        r"\usepackage{amsmath}",              
        r"\setmainfont{amssymb}",
])
from matplotlib.gridspec import GridSpec
import pandas as pd

import argparse
parser = argparse.ArgumentParser()
parser.add_argument("--input")
args = parser.parse_args()

df = pd.read_csv(args.input)

fig, ax = plt.subplots(figsize=[6.4,3.2])

for d, v in df.groupby("dim"):
    ax.scatter([d]*len(v), v["loss"], alpha=0.5, color="gray", facecolors="none")

avg = df.groupby("dim")["loss"].mean()
ax.plot(avg.index, avg)

ax.set_xlabel("Embeddings dimension ($L$)")
ax.set_ylabel("Skip-gram Word2Vec Loss")

fig.savefig("output/word2vec_validation.pdf", bbox_inches="tight")