Cosine metric - error "Negative values in data passed to precomputed distance matrix" about pynndescent

[lmcinnes]

Thanks, I'll try to look into this when I get a chance.

[j-adamczyk]

The dataset used was Codon Usage. Interestingly enough, it has only nonnegative values (codon percentages), so regular cosine is always nonnegative as well. Exact code:

import pandas as pd
from pynndescent import PyNNDescentTransformer
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
from pynndescent import PyNNDescentTransformer
from sklearn.pipeline import make_pipeline

df = pd.read_csv("codon_usage.csv")
df = df[pd.to_numeric(df["UUU"], errors="coerce").notnull()].copy()
df = df.copy()  # to avoid irritating SettingWithCopyWarning
df["UUU"] = df.loc[:, "UUU"].astype(float)
df["UUC"] = df.loc[:, "UUC"].astype(float)
df = df.loc[df["Ncodons"] >= 1000, :]
df = df.loc[df["Kingdom"] != "plm", :]
df = df.drop(["DNAtype", "SpeciesID", "Ncodons", "SpeciesName"], axis="columns")
kingdom_mapping = {
    "arc": 0,
    "bct": 1,
    "pln": 2,
    "inv": 2,
    "vrt": 2,
    "mam": 2,
    "rod": 2,
    "pri": 2,
    "phg": 3,
    "vrl": 4,
}
df = df.replace({"Kingdom": kingdom_mapping})
y = df.pop("Kingdom")


X_train, X_test, y_train, y_test = train_test_split(
    df, y, test_size=0.2, random_state=0, stratify=y
)

sklearn_knn = KNeighborsClassifier(metric="cosine")

pynndescent_ann = make_pipeline(
    PyNNDescentTransformer(metric="cosine", random_state=0),
    KNeighborsClassifier(metric="precomputed"),
)

sklearn_knn.fit(X_train, y_train)
pynndescent_ann.fit(X_train, y_train)