from sklearn.decomposition import PCA
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
from utilities import Timer, MetaData, ResultsWriter
# file properties
# -----------------------------------------------------
filePath = '../data/results.txt'
metadata = MetaData()
dataType = metadata.getResultColsDataType()
timer = Timer()
startTime = timer.getTime()
print('Start Time : ', timer.getTime()) # Get the start time for tracking purposes
print('------------------------------------------------------------')
print('Reading files ... ')
print('------------------------------------------------------------')
data = np.loadtxt(filePath, delimiter = ',', skiprows = 1, dtype=dataType)
df = pd.DataFrame(data)
# Separating the subject and activity
activity = df.ix[:,-1]%100
activity.name = 'predicted_activity'
subject = (df.ix[:,-1] - activity) / 100
subject.name = 'predicted_subj'
df = pd.concat([df,subject,activity], axis=1)
import time
from sklearn.model_selection import StratifiedShuffleSplit
from sklearn.multioutput import MultiOutputClassifier
from sklearn.naive_bayes import GaussianNB
from utilities import Timer, MetaData, ResultsWriter
# file properties
# -----------------------------------------------------
filePath = '../data/consolidated_clean_all.txt'
metadata = MetaData()
dataType = metadata.getProcessedColsDataType()
timer = Timer()
startTime = timer.getTime()
print('Start Time : ',
timer.getTime()) # Get the start time for tracking purposes
print('------------------------------------------------------------')
print('Reading files ... ')
print('------------------------------------------------------------')
# Note that this is a numpy structured array as the data set contains both int and float
# http://docs.scipy.org/doc/numpy/user/basics.rec.html
data = np.genfromtxt(filePath, delimiter=',', skip_header=1, dtype=dataType)
df = pd.DataFrame(data)
df.ix[:, :31] = (df.ix[:, :31] - df.ix[:, :31].mean()) / (df.ix[:, :31].max() -
df.ix[:, :31].min())
subj = df.ix[:, -2]
activity = df.ix[:, -1]
import numpy as np
import pandas as pd
from utilities import Timer, MetaData
# file properties
# -----------------------------------------------------
filePath = '../data/consolidated_all.txt'
outputFile = '../data/consolidated_clean_all.txt'
metadata = MetaData()
dataType = metadata.getOriginalColsDataType()
timer = Timer()
startTime = timer.getTime()
print('Start Time : ',
timer.getTime()) # Get the start time for tracking purposes
print('------------------------------------------------------------')
print('Reading files ... ')
print('------------------------------------------------------------')
# Note that this is a numpy structured array as the data set contains both int and float
# http://docs.scipy.org/doc/numpy/user/basics.rec.html
#activityData = np.genfromtxt(filePath, delimiter = ',', skip_header = 1, dtype=dataType)
activityData = np.loadtxt(filePath, delimiter=',', skiprows=1, dtype=dataType)
print('loading Time : ', timer.getTime())
# convert to pandas data frame
df = pd.DataFrame(activityData)
# count missing values in df
print('--------------------------------------')
