LDA topic modeling

Trains a latent Dirichlet allocation model with scikit-learn using abstracts from Neurosynth.

import os

import pandas as pd

from nimare import annotate
from nimare.dataset import Dataset
from nimare.utils import get_resource_path

Load dataset with abstracts

dset = Dataset(os.path.join(get_resource_path(), "neurosynth_laird_studies.json"))

Initialize LDA model

model = annotate.lda.LDAModel(n_topics=5, max_iter=1000, text_column="abstract")

Run model

new_dset = model.fit(dset)

View results

This DataFrame is very large, so we will only show a slice of it.

new_dset.annotations[new_dset.annotations.columns[:10]].head(10)

	id	study_id	contrast_id	Neurosynth_TFIDF__001	Neurosynth_TFIDF__01	Neurosynth_TFIDF__05	Neurosynth_TFIDF__10	Neurosynth_TFIDF__100	Neurosynth_TFIDF__11	Neurosynth_TFIDF__12
0	17029760-1	17029760	1	0.0	0.0	0.0	0.000000	0.0	0.000000	0.0
1	18760263-1	18760263	1	0.0	0.0	0.0	0.000000	0.0	0.000000	0.0
2	19162389-1	19162389	1	0.0	0.0	0.0	0.000000	0.0	0.176321	0.0
3	19603407-1	19603407	1	0.0	0.0	0.0	0.000000	0.0	0.000000	0.0
4	20197097-1	20197097	1	0.0	0.0	0.0	0.000000	0.0	0.000000	0.0
5	22569543-1	22569543	1	0.0	0.0	0.0	0.000000	0.0	0.000000	0.0
6	22659444-1	22659444	1	0.0	0.0	0.0	0.000000	0.0	0.000000	0.0
7	23042731-1	23042731	1	0.0	0.0	0.0	0.000000	0.0	0.000000	0.0
8	23702412-1	23702412	1	0.0	0.0	0.0	0.061006	0.0	0.000000	0.0
9	24681401-1	24681401	1	0.0	0.0	0.0	0.000000	0.0	0.000000	0.0

Given that this DataFrame is very wide (many terms), we will transpose it before presenting it.

model.distributions_["p_topic_g_word_df"].T.head(10)

	LDA5__1_human_functional_frontal	LDA5__2_connectivity_functional_anterior	LDA5__3_cortex_motor_network	LDA5__4_connectivity_cognitive_identified	LDA5__5_social_functional_connectivity
10	2.001000	0.001000	0.001000	0.001000	0.001000
abstract	0.001000	0.001000	0.001000	1.000975	1.001025
action	1.001168	1.000832	0.001000	0.001000	0.001000
active	0.001000	1.000409	2.001721	1.000871	0.001000
addition	0.001000	1.000148	1.000922	3.001929	0.001000
additionally	2.001000	0.001000	0.001000	0.001000	0.001000
affective	2.742754	1.258777	0.001000	0.001000	2.001469
affective processes	0.001000	2.001000	0.001000	0.001000	0.001000
ale	0.001000	0.001000	0.001000	1.000873	1.001127
altered	0.001000	0.001000	0.001000	0.001000	4.001000

n_top_terms = 10
top_term_df = model.distributions_["p_topic_g_word_df"].T
temp_df = top_term_df.copy()
top_term_df = pd.DataFrame(columns=top_term_df.columns, index=range(n_top_terms))
top_term_df.index.name = "Token"
for col in top_term_df.columns:
    top_tokens = temp_df.sort_values(by=col, ascending=False).index.tolist()[:n_top_terms]
    top_term_df.loc[:, col] = top_tokens

top_term_df

	LDA5__1_human_functional_frontal	LDA5__2_connectivity_functional_anterior	LDA5__3_cortex_motor_network	LDA5__4_connectivity_cognitive_identified	LDA5__5_social_functional_connectivity
Token
0	human	connectivity	cortex	connectivity	social
1	functional	functional	motor	cognitive	functional
2	frontal	anterior	network	identified	connectivity
3	maps	macm	control	stimulation	altered
4	cortex	functional connectivity	lateral	literature	structural
5	lateral	posterior	prefrontal	talairach	function
6	medial	seed	prefrontal cortex	error	indicate
7	cognitive	approaches	parietal	functional	modeling
8	memory	networks	cognition	published	network
9	frontal pole	connections	cortices	functions	analytic