Building Knowledge Graphs from Text

import networkx as nx
import numpy as np
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
from matplotlib.colors import LinearSegmentedColormap
from collections import Counter

FT_BG = '#FFF1E5'
FT_CLARET = '#990F3D'
FT_OXFORD = '#0F5499'
FT_TEAL = '#0D7680'

plt.rcParams.update({
    'figure.facecolor': FT_BG,
    'axes.facecolor': FT_BG,
    'savefig.facecolor': FT_BG,
    'font.family': 'sans-serif',
    'font.sans-serif': ['Helvetica Neue', 'Arial', 'sans-serif'],
    'axes.spines.top': False,
    'axes.spines.right': False,
})

corpus = [
    'Neural networks learn representations from data using backpropagation.',
    'Deep learning extends neural networks with multiple hidden layers.',
    'Backpropagation computes gradients for training deep learning models.',
    'Convolutional networks excel at image recognition and computer vision.',
    'Recurrent networks handle sequential data like text and time series.'
]

concepts = ['neural networks', 'deep learning', 'backpropagation', 'representations',
            'data', 'hidden layers', 'gradients', 'training', 'models',
            'convolutional networks', 'image recognition', 'computer vision',
            'recurrent networks', 'sequential data', 'text', 'time series']

freq = Counter()
G = nx.Graph()
for sent in corpus:
    lower = sent.lower()
    present = [c for c in concepts if c in lower]
    for c in present:
        freq[c] += 1
    for i, c1 in enumerate(present):
        for c2 in present[i+1:]:
            if G.has_edge(c1, c2):
                G[c1][c2]['weight'] += 1
            else:
                G.add_edge(c1, c2, weight=1)

for n in G.nodes():
    if n not in freq:
        freq[n] = 1

sizes = [freq[n] * 600 + 200 for n in G.nodes()]

ft_cmap = LinearSegmentedColormap.from_list('ft', [FT_OXFORD, FT_TEAL, FT_CLARET])

fig, ax = plt.subplots(figsize=(10, 7))
pos = nx.spring_layout(G, seed=42, k=2)
nx.draw_networkx_edges(G, pos, ax=ax, alpha=0.3, width=1.5)
nx.draw_networkx_nodes(G, pos, ax=ax, node_size=sizes,
                       node_color=list(range(len(G))),
                       cmap=ft_cmap, alpha=0.85)
nx.draw_networkx_labels(G, pos, ax=ax, font_size=8, font_color='#333333')
ax.set_axis_off()

fig.text(0.5, 0.97, 'Concept Co-occurrence Graph from ML Corpus',
         ha='center', fontsize=14, fontweight='bold', color='#333333')
fig.text(0.5, 0.935, 'Node size proportional to term frequency',
         ha='center', fontsize=10, color='#666666')
fig.text(0.02, 0.01, 'Source: Philip Jama via pjama.github.io',
         fontsize=8, color='#999999', ha='left')
fig.tight_layout(rect=[0, 0.03, 1, 0.92])
fig.savefig('concept_cooccurrence.png', dpi=150, bbox_inches='tight')

print('wrote concept_cooccurrence.png')

import networkx as nx
import numpy as np
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt

FT_BG = '#FFF1E5'
FT_CLARET = '#990F3D'
FT_OXFORD = '#0F5499'
FT_TEAL = '#0D7680'
FT_CANDY = '#FF7FAA'

plt.rcParams.update({
    'figure.facecolor': FT_BG,
    'axes.facecolor': FT_BG,
    'savefig.facecolor': FT_BG,
    'font.family': 'sans-serif',
    'font.sans-serif': ['Helvetica Neue', 'Arial', 'sans-serif'],
    'axes.spines.top': False,
    'axes.spines.right': False,
})

G = nx.DiGraph()
edges = [
    ('Python', 'NumPy', 'has_lib'), ('Python', 'Pandas', 'has_lib'),
    ('Python', 'Scikit-learn', 'has_lib'), ('Python', 'TensorFlow', 'has_lib'),
    ('NumPy', 'Arrays', 'provides'), ('Pandas', 'DataFrames', 'provides'),
    ('Scikit-learn', 'Classification', 'supports'), ('Scikit-learn', 'Regression', 'supports'),
    ('TensorFlow', 'Neural Nets', 'builds'), ('TensorFlow', 'GPU', 'uses'),
    ('Neural Nets', 'Deep Learning', 'enables'), ('Deep Learning', 'NLP', 'applied_to'),
    ('Deep Learning', 'Vision', 'applied_to'), ('Classification', 'Supervised', 'is_type'),
    ('Regression', 'Supervised', 'is_type'), ('NLP', 'Transformers', 'uses'),
    ('Vision', 'CNNs', 'uses'), ('Supervised', 'ML', 'is_type'),
    ('Deep Learning', 'ML', 'is_type'), ('NumPy', 'Linear Algebra', 'provides')
]
for u, v, r in edges:
    G.add_edge(u, v, relation=r)

Gu = G.to_undirected()
comms = nx.community.louvain_communities(Gu, seed=42)
ft_palette = [FT_OXFORD, FT_CLARET, FT_TEAL, FT_CANDY]
node_color_map = {}
for i, comm in enumerate(comms):
    for n in comm:
        node_color_map[n] = ft_palette[i % len(ft_palette)]

fig, ax = plt.subplots(figsize=(12, 8))
pos = nx.spring_layout(G, seed=42, k=1.8)
colors = [node_color_map.get(n, '#999') for n in G.nodes()]
nx.draw_networkx_edges(G, pos, ax=ax, alpha=0.3, width=1, arrows=True,
                       arrowsize=12, connectionstyle='arc3,rad=0.1')
nx.draw_networkx_nodes(G, pos, ax=ax, node_color=colors,
                       node_size=400, alpha=0.85)
nx.draw_networkx_labels(G, pos, ax=ax, font_size=7, font_color='#333333')
edge_labels = {(u, v): d['relation'] for u, v, d in G.edges(data=True)}
nx.draw_networkx_edge_labels(G, pos, edge_labels, ax=ax, font_size=6, alpha=0.7)
ax.set_axis_off()

fig.text(0.5, 0.97, 'Knowledge Graph with Community Coloring',
         ha='center', fontsize=14, fontweight='bold', color='#333333')
fig.text(0.5, 0.935, 'Louvain communities on a Python/ML entity graph',
         ha='center', fontsize=10, color='#666666')
fig.text(0.02, 0.01, 'Source: Philip Jama via pjama.github.io',
         fontsize=8, color='#999999', ha='left')
fig.tight_layout(rect=[0, 0.03, 1, 0.92])
fig.savefig('knowledge_graph_communities.png', dpi=150, bbox_inches='tight')

print('wrote knowledge_graph_communities.png')