def compute_events(data_dir, start_key, end_key, label='', output_dir=None):
if output_dir != None:
make_dir(output_dir)
df_merged = pd.DataFrame()
for csv in os.listdir(data_dir):
ha = HeadAnnotator()
if not csv.find('.csv') == -1:
fi_path = '%s/%s' % (data_dir, csv)
df = pd.read_csv(fi_path)
ha = HeadAnnotator()
event_hash, event_list = ha.annotate_events(df)
df_p = ha.df
og_cols = df.columns.tolist()
fe_cols = df_p.columns.tolist()
print event_hash
for c in og_cols:
if not c in fe_cols:
df_p[c] = df[c]
if output_dir != None:
sub_dir = '%s/events' % output_dir
make_dir(sub_dir)
# assume start key and end key event s have the same
for i in xrange(len(event_hash[start_key])):
if len(event_hash[end_key]) > i:
start = event_hash[start_key][i]
end = event_hash[end_key][i]
df_sub = df_p.loc[start:end]
df_sub['original_index'] = df_sub.index
# add a class so the training data is 'labeled'
df_sub['turn_sentiment'] = label
print csv
df_sub.to_csv('%s/%s-%s.csv' % (sub_dir, csv.split('.')[0], i), index=False)
if output_dir != None:
df_p.to_csv('%s/%s' % (output_dir, csv), index=False)
visualize.plot_diagnostics(df_p, ha.active_features, '%s/%s' % (output_dir,csv.split('.')[0]), y_col='noseX')
df_merged = pd.concat([df_merged, df_p])
return df_merged
def print_test_data(m_df, cf, cf_string):
Y_test = cf.predict(m_df[active_cols])
print cf_string, ' accuracy', \
np.sum(Y_test == m_df['class']) / float(len(m_df))
df_test['class'] = Y_test
plot_diagnostics(df_test, active_cols, '%s/head-turn-test-%s' % (base_dir, cf_string))
# the directory (labeled data) we are looking to load head turns from
data_dir = sys.argv[1]
# number of clusters to cluster the data on
k = int(sys.argv[2])
base_dir = "data" # dir to read data from
m_dir = "%s/%s" % (base_dir, data_dir)
output_dir = "data/merged"
ignore_columns = [
"date",
"frameIndex",
"class",
"time",
"noseX_raw",
"noseY_raw",
"faceBottom",
"faceTop",
"faceLeft",
"faceRight",
"noseX",
"noseY",
"isFrontFace",
]
df, active_features = generate_training_set(
m_dir, k=k, window_size=window_size, relevant_features=relevant_features
)
df.to_csv("%s/%s.csv" % (output_dir, data_dir), index=False)
plot_diagnostics(df, active_features, "%s/%s" % (output_dir, data_dir))
config["active_features"] = active_features
with open("config.json", "w") as outfile:
json.dump(config, outfile)
