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_functional_connectivity_identified	LDA5__2_functional_connectivity_anterior	LDA5__3_connectivity_functional_order	LDA5__4_connectivity_functional_posterior	LDA5__5_cortex_lateral_systems
10	1.001056	1.000944	0.001000	0.001000	0.001000
abstract	1.001157	1.000843	0.001000	0.001000	0.001000
action	0.001000	1.000963	0.001000	1.001037	0.001000
active	1.000920	1.000907	0.001000	2.001173	0.001000
addition	2.001262	1.000518	0.001000	0.999899	1.002321
additionally	0.001000	0.001000	1.001482	1.000518	0.001000
affective	2.000998	3.000626	1.001376	0.001000	0.001000
affective processes	0.001000	0.001000	1.001329	1.000671	0.001000
ale	1.001092	0.001000	0.001000	1.000908	0.001000
altered	3.001703	0.001000	0.001000	1.000297	0.001000

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_functional_connectivity_identified	LDA5__2_functional_connectivity_anterior	LDA5__3_connectivity_functional_order	LDA5__4_connectivity_functional_posterior	LDA5__5_cortex_lateral_systems
Token
0	functional	functional	connectivity	connectivity	cortex
1	connectivity	connectivity	functional	functional	lateral
2	identified	anterior	order	posterior	systems
3	functions	human	cognitive	macm	cognition
4	cognitive	social	human	connections	network
5	cbp	seed	memory	method	cortices
6	analytic	networks	lateral	behavioral	thalamus
7	resting	approaches	patterns	using	level
8	stimulation	motor	medial	functional connectivity	anterior
9	parcellation	insula	published	literature	insula