Makefile

.PHONY: all parse embed reduce reduce-tsne reduce-both reduce-3d reduce-ft visualize visualize-3d dash folio analyze bigrams similarity section-vocab vocab-drift nn-graph embed-ft word-families pmi function-words entropy-scatter report analogy char-ngrams line-structure positional-bigrams cooccurrence hapax word-length hmm word-transition cluster-purity context-profile folio-drift morpheme section-distance word-fingerprint word-roles phonotactics line-entropy line-clusters lm-perplexity embed-stability cross-section folio-richness line-similarity paradigm-finder semantic-fields entropy-rate changepoint topic-model char-position-entropy sif-embeddings word-sequence-model word-burstiness affix-entropy folio-similarity-matrix zipf-analysis prefix-suffix-matrix line-position-words cv-skeleton word-network-centrality ppmi-vectors context-asymmetry surprisal-map portal clean help

all: parse embed reduce visualize

parse:
	python3 src/core/parse.py

embed: parse
	python3 src/core/embed.py

reduce: embed
	python3 src/core/reduce.py

reduce-tsne: embed
	python3 src/core/reduce.py --tsne

reduce-both: embed
	python3 src/core/reduce.py --both

visualize: reduce
	python3 src/viz/visualize.py

dash: reduce
	python3 src/viz/visualize_dash.py

folio: embed
	python3 src/core/folio_embed.py

analyze: embed
	python3 src/analysis/analyze.py

bigrams: parse
	python3 src/analysis/bigrams.py

similarity: embed
	python3 src/analysis/similarity_matrix.py

section-vocab: parse
	python3 src/analysis/section_vocab.py

vocab-drift: parse
	python3 src/analysis/vocab_drift.py

nn-graph: reduce
	python3 src/analysis/nn_graph.py

embed-ft: parse
	python3 src/core/embed_fasttext.py

reduce-ft: embed-ft
	python3 src/core/reduce.py --ft

word-families: embed-ft
	python3 src/analysis/word_families.py

pmi: parse
	python3 src/analysis/pmi.py

function-words: parse word-families
	python3 src/analysis/function_words.py

entropy-scatter: embed
	python3 src/analysis/entropy_scatter.py

report: embed word-families pmi
	python3 src/viz/report.py

portal: report
	python3 src/viz/portal.py

analogy: embed-ft
	python3 src/cli/analogy_discover.py

char-ngrams: parse
	python3 src/analysis/char_ngrams.py

line-structure: parse word-families
	python3 src/analysis/line_structure.py

positional-bigrams: parse
	python3 src/analysis/positional_bigrams.py

cooccurrence: parse
	python3 src/analysis/cooccurrence_network.py

hapax: parse
	python3 src/analysis/hapax_analysis.py

word-length: parse
	python3 src/analysis/word_length_profile.py

hmm: embed
	python3 src/analysis/hidden_markov.py

reduce-3d: embed
	python3 src/core/reduce.py --3d

visualize-3d: reduce-3d
	python3 src/viz/visualize_3d.py

word-transition: embed
	python3 src/analysis/word_transition.py

cluster-purity: embed hmm
	python3 src/analysis/cluster_purity.py

context-profile: parse
	python3 src/analysis/context_profile.py

folio-drift: embed
	python3 src/analysis/folio_centroid_drift.py

morpheme: parse
	python3 src/analysis/morpheme_inventory.py

section-distance: embed word-families
	python3 src/analysis/section_distance.py

word-fingerprint: embed word-families pmi
	python3 src/analysis/word_fingerprint.py $(word)

word-roles: embed
	python3 src/analysis/word_roles.py

phonotactics: parse
	python3 src/analysis/phonotactics.py

line-entropy: parse
	python3 src/analysis/line_entropy.py

line-clusters: embed
	python3 src/analysis/line_clusters.py

lm-perplexity: parse
	python3 src/analysis/lm_perplexity.py

embed-stability: embed
	python3 src/analysis/embed_stability.py

cross-section: embed
	python3 src/analysis/cross_section.py

folio-richness: parse
	python3 src/analysis/folio_richness.py

line-similarity: line-clusters
	python3 src/analysis/line_similarity.py

paradigm-finder: embed
	python3 src/analysis/paradigm_finder.py

semantic-fields: embed
	python3 src/analysis/semantic_fields.py

entropy-rate: parse
	python3 src/analysis/entropy_rate.py

changepoint: embed
	python3 src/analysis/changepoint.py

topic-model: parse embed
	python3 src/analysis/topic_model.py

char-position-entropy: parse
	python3 src/analysis/char_position_entropy.py

sif-embeddings: embed
	python3 src/analysis/sif_embeddings.py

word-sequence-model: parse
	python3 src/analysis/word_sequence_model.py

word-burstiness: parse
	python3 src/analysis/word_burstiness.py

affix-entropy: parse
	python3 src/analysis/affix_entropy.py

folio-similarity-matrix: embed
	python3 src/analysis/folio_similarity_matrix.py

zipf-analysis: parse
	python3 src/analysis/zipf_analysis.py

prefix-suffix-matrix: parse
	python3 src/analysis/prefix_suffix_matrix.py

line-position-words: embed
	python3 src/analysis/line_position_words.py

cv-skeleton: parse
	python3 src/analysis/cv_skeleton.py

word-network-centrality: parse
	python3 src/analysis/word_network_centrality.py

ppmi-vectors: embed
	python3 src/analysis/ppmi_vectors.py

context-asymmetry: embed
	python3 src/analysis/context_asymmetry.py

surprisal-map: parse
	python3 src/analysis/surprisal_map.py

clean:
	rm -rf data/ index.html voynich_embeddings.html folio_embeddings.html \
	       bigrams_heatmap.html bigrams_network.html \
	       similarity_matrix.html section_vocab.html \
	       vocab_drift.html nn_graph.html \
	       word_families.html pmi_heatmap.html \
	       function_words.html entropy_scatter.html report.html \
	       char_ngrams.html line_structure.html \
	       positional_bigrams.html cooccurrence_network.html \
	       hapax_analysis.html word_length_profile.html hmm_states.html \
	       voynich_3d.html word_transition.html \
	       cluster_purity.html context_profile.html \
	       folio_drift.html morpheme_inventory.html \
	       section_distance.html word_roles.html phonotactics.html \
	       line_entropy.html line_clusters.html lm_perplexity.html \
	       embed_stability.html cross_section.html \
	       folio_richness.html line_similarity.html \
	       paradigm_finder.html semantic_fields.html \
	       entropy_rate.html changepoint.html \
	       topic_model.html char_position_entropy.html \
	       sif_embeddings.html word_sequence_model.html \
	       word_burstiness.html affix_entropy.html \
	       folio_similarity_matrix.html zipf_analysis.html \
	       prefix_suffix_matrix.html line_position_words.html \
	       cv_skeleton.html word_network_centrality.html \
	       ppmi_vectors.html context_asymmetry.html \
	       surprisal_map.html

help:
	@echo "Voynich Embedding Pipeline"
	@echo ""
	@echo "  make all          parse → embed → UMAP → visualize (static HTML)"
	@echo "  make reduce-both  run both UMAP and t-SNE reductions"
	@echo "  make dash         interactive Dash app at http://127.0.0.1:8050"
	@echo "  make folio        folio-level embedding visualization"
	@echo "  make analyze      EVA prefix/suffix pattern analysis"
	@echo "  make bigrams      bigram frequency + heatmap + network"
	@echo "  make similarity   pairwise cosine similarity heatmap (top-N words)"
	@echo "  make section-vocab  TF-IDF-style distinctive vocabulary per section"
	@echo "  make vocab-drift  word frequency drift across folio windows"
	@echo "  make nn-graph     K-nearest-neighbour graph in UMAP space"
	@echo "  make embed-ft     FastText character-ngram embeddings"
	@echo "  make reduce-ft    UMAP reduction of FastText embeddings"
	@echo "  make word-families  morphological word families via FastText clustering"
	@echo "  make pmi          Pointwise Mutual Information bigram analysis"
	@echo "  make function-words  initial-fraction vs entropy scatter (function-word ID)"
	@echo "  make entropy-scatter prev vs next entropy asymmetry (directional)"
	@echo "  make report       HTML summary dashboard linking all outputs"
	@echo "  make portal       generate searchable HTML portal (index.html) linking all analyses"
	@echo "  make analogy      morphological offset coherence (w2v vs FastText)"
	@echo "  make char-ngrams  EVA character n-gram analysis + transition heatmap"
	@echo "  make line-structure  first/last word + line-length + template analysis"
	@echo "  make positional-bigrams  G² enrichment of bigrams by line zone"
	@echo "  make cooccurrence    word co-occurrence network + community detection"
	@echo "  make hapax           Zipf / Heap / hapax legomena frequency analysis"
	@echo "  make word-length     word-length by section / position / folio trend"
	@echo "  make hmm             unsupervised HMM (K=6 latent POS-like states)"
	@echo "  make reduce-3d       UMAP 3D reduction of word2vec embeddings"
	@echo "  make visualize-3d    interactive 3D scatter (section/freq/prefix/HMM)"
	@echo "  make word-transition directed word transition probability network"
	@echo "  make cluster-purity  ARI/NMI of KMeans vs section/HMM/prefix/length"
	@echo "  make context-profile left/right context probability heatmap"
	@echo "  make folio-drift     folio semantic trajectory (PCA of mean embeddings)"
	@echo "  make morpheme        EVA morpheme candidates via char n-gram segmentation"
	@echo "  make section-distance  pairwise section distance matrices (6 metrics)"
	@echo "  make word-fingerprint word=<word>  multi-signal fingerprint card per word"
	@echo "  make word-roles      GMM functional role clustering (BIC-selected K)"
	@echo "  make phonotactics    EVA phonotactic patterns: positional bias, trigram log-odds, CV shapes"
	@echo "  make line-entropy    line-slot entropy, adjacent Jaccard, repetition rate, first-word PMI"
	@echo "  make line-clusters   line-embedding UMAP + KMeans (K=7) section recovery"
	@echo "  make lm-perplexity   Kneser-Ney bigram LM perplexity scoring per line"
	@echo "  make embed-stability bootstrap embedding stability (15 models, K=10 neighbors)"
	@echo "  make cross-section   chi² section exclusivity, TF-IDF, overlap, border words"
	@echo "  make folio-richness  per-folio TTR, MSTTR, hapax rate, entropy, Yule's K"
	@echo "  make line-similarity near-duplicate and exact-copy line detection"
	@echo "  make paradigm-finder suffix/prefix paradigm detection via embedding offsets"
	@echo "  make semantic-fields hierarchical dendrogram of top-200 words (Ward/cosine)"
	@echo "  make entropy-rate    block entropy H(n) and entropy rate estimation"
	@echo "  make changepoint     folio embedding change-point detection (MMD + CUSUM)"
	@echo "  make clean        remove all generated data/ and HTML files"
	@echo ""
	@echo "CLI tools:"
	@echo "  python3 src/cli/neighbors.py daiin                 nearest neighbours"
	@echo "  python3 src/cli/neighbors.py --cluster 8           KMeans vocabulary clusters"
	@echo "  python3 src/cli/neighbors.py --analogy A B C       vector analogy A - B + C = ?"
	@echo "  python3 src/cli/neighbors.py --interpolate A B N   semantic path A → B in N steps"