def annotate_events(self, df):
window_size = self.window_size
active_features = self.active_features
og_cols = df.columns.tolist()
df_feat, features = head_features.apply_feature_engineering(
df,
relevant_features=self.relevant_features,
)
df_feat.fillna(0, inplace=True)
df_w, feats = head_features.generate_windows(
df_feat,
window = window_size,
relevant_features=features,
)
# Cut off the tail end of the data (lots of null values)
df_w = df_w.loc[0:(len(df_w)-window_size)]
Y = self.model.predict(df_w[active_features])
df_w['class'] = Y
for c in og_cols:
if not c in active_features:
df_w[c] = df[c]
self.df = df_w
print Y
# These are the raw events
return self.find_true_events(df, Y.tolist(), index_col='frameIndex')
def generate_training_set(
director,
feature_generator=lambda df, cols: head_features.apply_feature_engineering(df, cols),
k=4,
window_size=10,
relevant_features=[],
verbose=True,
):
"""
Given the directory of data files,
cluster the event points and saves the results
in the merged folder. It appends an extra `class` column
to represente the labeling results.
"""
training_data = pd.DataFrame()
active_features = []
for csv in os.listdir(director):
if not csv.find(".csv") == -1:
fi_path = "%s/%s" % (director, csv)
df = pd.read_csv(fi_path)
if verbose:
print fi_path
# Save to raw so the original data is kept. We are interested in
# keeping the original data for these rows
df["noseX_raw"] = df["noseX"]
df["noseY_raw"] = df["noseY"]
# features
df, active_features = feature_generator(df, relevant_features)
df.fillna(0, inplace=True)
df_w, active_features = head_features.generate_windows(
df, window=window_size, relevant_features=active_features
)
df_trimmed = df_w.loc[0 : (len(df_w) - window_size)]
# cluster individiaul files
Y = cluster_training_signals(df_trimmed, active_features, k)
df_trimmed["class"] = Y
training_data = pd.concat([training_data, df_trimmed])
df_w = training_data
if verbose:
print "Now clustering the data"
# active_columns = get_active_features(df, ignore_columns)
# cluster all together
print "Number of data points clustered:", len(df_w)
print "Features used to cluster:\n"
for c in active_features:
print "\t%s" % c
return df_w, active_features
