Created
October 4, 2019 12:46
-
-
Save Ken-Kuroki/d549805317e139dda425e8ddb86520a3 to your computer and use it in GitHub Desktop.
Generate iTOL "binary data" annotation file from pandas dataframe
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import numpy as np | |
import pandas as pd | |
from ete3 import PhyloTree | |
def generate_binary(df: pd.DataFrame, save_file: str) -> None: | |
# df columns must be labels, values, values, ..., values. | |
num_cols = df.shape[1]-1 | |
shapes = ",".join(["1"]*num_cols) | |
colors = ",".join(["#ff0000"]*num_cols) | |
labels = ",".join([f"{i+1}" for i in range(num_cols)]) | |
output = f"""DATASET_BINARY\n | |
SEPARATOR COMMA\n | |
DATASET_LABEL,label_binary\n | |
COLOR,{colors}\n | |
FIELD_SHAPES,{shapes}\n | |
FIELD_LABELS,{labels}\n | |
DATA\n""" + df.to_csv(header=False, index=False) | |
with open(save_file, "w") as f: | |
f.write(output) | |
# tree = PhyloTree("tree.nwk") | |
# leaf_labels = [leaf.name for leaf in tree.get_leaves()] | |
leaf_labels = ["A", "B", "D", "E"] | |
matrix = np.random.randint(0, 2, size=(len(leaf_labels),100)) | |
generate_binary(pd.concat([pd.Series(leaf_labels), pd.DataFrame(matrix)], axis=1), "binary.txt") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment