def predict_missing_links(train_file_path, evaluation_file_path, model_path,
tensorboard_visualizations_path):
graph = load_from_csv('.', train_file_path, sep=',')
evaluation_samples = load_from_csv('.', evaluation_file_path, sep=',')
print('Head of the loaded graph: ')
print(graph[:5])
train_samples, test_samples = split(graph)
print(
f'Divided into train and test subsets with shapes {train_samples.shape} and {test_samples.shape} respectively.'
)
if not os.path.isfile(model_path):
model = train_transe(train_samples) # train_complex(train_samples)
save_model(model, model_path)
else:
model = restore_model(model_path)
metrics = compute_metrics(model, train_samples, test_samples)
print(f'{"metric":10s}: {"score":5s}')
for metric, score in metrics.items():
print(f'{metric:10s}: {score:<5.2f}')
scores, ranks = score_samples(model, evaluation_samples, train_samples)
evaluation_summary = summarize(scores, evaluation_samples, ranks)
print(evaluation_summary)
if tensorboard_visualizations_path:
os.makedirs(tensorboard_visualizations_path, exist_ok=True)
create_tensorboard_visualizations(model,
tensorboard_visualizations_path)
def main():
network = read_network()
positives_filter = load_from_csv('.', 'network.csv', sep=',')
#generate_model(positives_filter)
model = load_model()
window = Tk()
window.title("Match Makers")
window.geometry('350x200')
lbl = Label(window, text="Name")
lbl.grid(column=0, row=0)
target = Entry(window, width=30)
target.grid(column=1, row=0)
lbl2 = Label(window, text="Topic")
lbl2.grid(column=0, row=1)
topic = Entry(window, width=30)
topic.grid(column=1, row=1)
lbl3 = Label(window, text="Results")
lbl3.grid(column=0, row=3)
results = scrolledtext.ScrolledText(window, width=40, height=10)
results.grid(column=0, row=4)
def clicked():
#res = "Welcome to " + target.get()
reccomendations = generate_reccomendations(network, model,
positives_filter,
target.get(), topic.get())
if len(reccomendations) > 5:
reccomendations = reccomendations[:5]
final_result = "\n".join(reccomendations)
results.delete(1.0, END)
results.insert(INSERT, final_result)
btn = Button(window, text="Process", command=clicked)
btn.grid(column=0, row=2)
window.mainloop()
# !pip install ampligraph;
import numpy as np
import pandas as pd
import ampligraph
ampligraph.__version__
"""## 1. Dataset exploration"""
import requests
from ampligraph.datasets import load_from_csv
url = 'https://ampligraph.s3-eu-west-1.amazonaws.com/datasets/GoT.csv'
open('GoT.csv', 'wb').write(requests.get(url).content)
X = load_from_csv('.', 'GoT.csv', sep=',')
X[:5, ]
"""Subject and object entities in the dataset:"""
entities = np.unique(np.concatenate([X[:, 0], X[:, 2]]))
entities
"""Relationships that link subject and object"""
relations = np.unique(X[:, 1])
relations
"""---
# 2. Defining train and test datasets
"""
import numpy as np
import pandas as pd
import requests
from ampligraph.datasets import load_from_csv
from ampligraph.latent_features import HolE, ComplEx
from ampligraph.evaluation import evaluate_performance
from ampligraph.evaluation import mr_score, mrr_score, hits_at_n_score
from ampligraph.evaluation import train_test_split_no_unseen
# International football matches triples
url = 'https://ampligraph.s3-eu-west-1.amazonaws.com/datasets/football.csv'
open('football.csv', 'wb').write(requests.get(url).content)
X = load_from_csv('.', 'football.csv', sep=',')[:, 1:]
# Train test split
X_train, X_test = train_test_split_no_unseen(X, test_size=10000)
# ComplEx model
model = HolE(batches_count=50,
epochs=300,
k=100,
eta=20,
optimizer='adam',
optimizer_params={'lr': 1e-4},
loss='multiclass_nll',
regularizer='LP',
regularizer_params={
'p': 3,
'lambda': 1e-5
},