def draw_stacked_chart(df, file_name, minimum_feature_contribution):
logger.info('drawing stacked chart for ' + file_name)
col_list, remaining_features, remaining_features_values = va_utils.get_significant_features(df, minimum_feature_contribution)
X = list(df['Date'])
data = OrderedDict()
for col in col_list:
data[col] = df[col]
#finally add the remaining features as a combined single column
data['everything-else'] = remaining_features_values
feature_name = file_name[:-4]
#chart_file_name = feature_name + '.html'
#output_file(chart_file_name)
file_name_wo_extn = file_name[:-4]
chart_file_name = os.path.join(os.path.sep, os.getcwd(), OUTPUT_DIR_NAME, file_name_wo_extn + '_stacked_chart.html')
output_file(chart_file_name)
title = feature_name.upper() + ' distribution from ' + str(df['Date'][0]) + ' to ' + str(df['Date'][len(df) - 1])
bar = Bar(data, X, title= title, stacked=True, legend='bottom_left', tools='hover,pan,wheel_zoom,box_zoom,reset,resize', width=1300, height=500)
# glyph_renderers = bar.select(dict(type=GlyphRenderer))
# bar_source = glyph_renderers[0].data_source
# hover = bar.select(dict(type=HoverTool))
# hover.tooltips = [
# ('name',' @cat'),
# ('number', '$y'),
# ]
save(bar)
logger.info('saved the chart in ' + chart_file_name)
def model_tsa(df, file_name, minimum_feature_contribution):
#first get a list of features to model
#each significant feature (protocol or application) would be modeled as an ARIMA (auto regressive moving average)
#the modeling artifacts i.e. charts, sumary etc would be stored in a directory by feature name
logger.info('Begin feature extraction...')
col_list, remaining_features, remaining_features_values = va_utils.get_significant_features(df, minimum_feature_contribution)
#store the results in a dataframe
df_output = pd.DataFrame()
feature_name_list = []
model_name_list = []
MAE_list = []
model_selection_list = []
predicted_col_list_with_data = ['Date'] + col_list
df_predictions = pd.DataFrame(columns = predicted_col_list_with_data )
logger.info('columns in oredicted df...')
logger.info(predicted_col_list_with_data)
df3 = df_predictions
#df_w_predictions = copy.deepcopy(df[col_list])
for col in col_list:
logger.info('-------- modeling ' + col + '-------------')
curr_dir = os.getcwd()
try:
feature, model_names, models, results, MAE, predicted_dates, predicted, model_selection = model_feature(file_name, df, col)
feature_name_list += [feature]*len(model_names)
model_name_list += model_names
MAE_list += MAE
model_selection_list += model_selection
df_predictions['Date'] = predicted_dates
df_predictions[feature] = predicted
except Exception, e:
logger.info('Could not model feature ' + col)
logger.info('Exception: ' + str(e))
os.chdir(curr_dir)
