def run_ds_pipeline(config):
#get logger object, probably already created
logger = sa_logger.init(globals.PACKAGE_NAME)
logger.info('Data science pipeline begining...')
#initialize db
dbif.db_init()
if config['action']['ingest']['make_list'] == True:
#begin with data ingestion
ingest.ingest_data(config)
else:
print 'skipping ingestion...'
if config['action']['wrangle']['transform'] == True:
#time for data wrangling
wrangle.wrangle_data(config)
else:
logger.info('skipping wrangling and insertion of data into db ...')
if config['action']['analyze']['analyze'] == True:
#time for data analysis
analyze.analyze_data(config)
else:
logger.info('skipping analysis ...')
if config['action']['visualize']['visualize'] == True:
#time for data visualization
visualize_and_analyze.visualize_data(config)
else:
logger.info('skipping visualization ...')
import va_utils
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
from scipy import stats
import matplotlib.pyplot as plt
import statsmodels.api as sm
from sklearn import linear_model
#global varialbes for this file
logger = sa_logger.init(globals.PACKAGE_NAME)
OUTPUT_DIR_NAME = "output"
def do_linear_regression(file_name):
try:
logger.info('-------------------------------------')
logger.info('TCP Vs UDP linear regression.........')
logger.info('-------------------------------------')
df = pd.read_csv(file_name)
#plot TCP Vs UDP, so UDP goes on x axis
x = np.array(df['UDP'])
X = x[:, np.newaxis]
y = np.array(df['TCP'])
#create a linear regressor
