-
Notifications
You must be signed in to change notification settings - Fork 0
/
core.py
65 lines (47 loc) · 3.28 KB
/
core.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
"""
Example of training a model using this package.
"""
from Pinpoint.FeatureExtraction import *
from Pinpoint.RandomForest import *
# Performs feature extraction from the provided Extremist, Counterpoise, and Baseline datasets.
extractor = feature_extraction(violent_words_dataset_location=r"datasets/swears",
baseline_training_dataset_location=r"datasets/far-right/LIWC2015 Results (Storm_Front_Posts).csv")
extractor.MAX_RECORD_SIZE = 250000
extractor.dump_training_data_features(
feature_file_path_to_save_to=r"outputs/training_features.json",
extremist_data_location=r"datasets/far-right/LIWC2015 Results (extreamist-messages.csv).csv",
baseline_data_location=r"datasets/far-right/LIWC2015 Results (non-extreamist-messages.csv).csv")
# Trains a model off the features file created in the previous stage
model = random_forest()
model.RADICAL_LANGUAGE_ENABLED = True
model.BEHAVIOURAL_FEATURES_ENABLED = True
model.PSYCHOLOGICAL_SIGNALS_ENABLED = True
model.train_model(features_file= r"outputs/training_features.json",
force_new_dataset=True, model_location=r"outputs/far-right-baseline.model") # , model_location=r"Pinpoint/model/my.model"
model.create_model_info_output_file(location_of_output_file="outputs/far-right-baseline-output.txt",
training_data_csv_location=r"outputs/training_features.json.csv")
#############################################################################################
model.RADICAL_LANGUAGE_ENABLED = False
model.BEHAVIOURAL_FEATURES_ENABLED = True
model.PSYCHOLOGICAL_SIGNALS_ENABLED = False
model.train_model(features_file= r"outputs/training_features.json",
force_new_dataset=True, model_location=r"outputs/far-right-behavioural.model") # , model_location=r"Pinpoint/model/my.model"
model.create_model_info_output_file(location_of_output_file="outputs/far-right-behavioural-output.txt",
training_data_csv_location=r"outputs/training_features.json.csv")
############################################################################
model.RADICAL_LANGUAGE_ENABLED = False
model.BEHAVIOURAL_FEATURES_ENABLED = False
model.PSYCHOLOGICAL_SIGNALS_ENABLED = True
model.train_model(features_file= r"outputs/training_features.json",
force_new_dataset=True, model_location=r"outputs/far-right-psychological.model") # , model_location=r"Pinpoint/model/my.model"
model.create_model_info_output_file(location_of_output_file="outputs/far-right-psychological-output.txt",
training_data_csv_location=r"outputs/training_features.json.csv")
##############################################################################################
model.RADICAL_LANGUAGE_ENABLED = True
model.BEHAVIOURAL_FEATURES_ENABLED = False
model.PSYCHOLOGICAL_SIGNALS_ENABLED = False
model.train_model(features_file= r"outputs/training_features.json",
force_new_dataset=True, model_location=r"outputs/far-right-radical-language.model") # , model_location=r"Pinpoint/model/my.model"
model.create_model_info_output_file(location_of_output_file="outputs/far-right-radical-language-output.txt",
training_data_csv_location=r"outputs/training_features.json.csv")
print("Finished")