def main():
d = Data('cars.csv')
print "Raw Headers"
print d.get_raw_headers()
print "\n\n"
print "Raw number of columns"
print d.get_raw_num_columns()
print "\n\n"
print "Raw number of rows"
print d.get_raw_num_rows()
print "\n\n"
print "13th row"
print d.get_raw_row(13)
print "\n\n"
print "Value at row 6, header 'Car'"
print d.get_raw_value(6, 'Car')
print "\n\n"
print "Matrix data"
print d.matrix_data
print "\n\n"
print "Headers"
print d.get_headers()
print "\n\n"
print "Number of cols"
print d.get_num_columns()
print "\n\n"
print "5th row"
print d.get_row(5)
print "\n\n"
print "Get value"
print d.get_value(5, 'Horsepower')
print "\n\n"
print "get_data function"
print d.get_data(['Origin', 'Horsepower'])
print "\n\n"
print "data range"
print analysis.data_range(d, ['Origin', 'Horsepower'])
print "\n\n"
print "mean of horsepower and origin"
print analysis.mean(d, ['Horsepower', 'Origin'])
print "\n\n"
print "standard deviation for horsepower and origin"
print analysis.stdev(d, ['Horsepower', 'Origin'])
print "\n"
print "normalized columns origin and horsepower"
print analysis.normalize_columns_separately(d, ['Origin', 'Horsepower'])
print "\n\n"
print "normalized together origin and horsepower"
print analysis.normalize_columns_together(d, ['Origin', 'Horsepower'])
print "\n\n"
print "median of columns origin, horspower and weight"
print analysis.median(d, ['Origin', 'Horsepower', 'Weight'])
print d.get_data(['Origin', 'Horsepower']).shape
def main(argv):
# test command line arguments
if len(argv) < 2:
print('Usage: python %s <csv filename>' % (argv[0]))
exit(0)
# create a data object, which reads in the data
dobj = data.Data(argv[1])
# print out information about the data
print('Number of rows: ', dobj.get_num_points())
print('Number of columns: ', dobj.get_num_dimensions())
# print out the headers
print("\nHeaders:")
headers = dobj.get_headers()
s = headers[0]
for header in headers[1:]:
s += ", " + header
print(s)
# print out the types
print("\nTypes")
types = dobj.get_types()
s = types[0]
for type in types[1:]:
s += ", " + type
print(s)
# print out a single row
print("\nPrinting row index 2")
print(dobj.get_row(2))
# print out all of the data
print("\nData")
headers = dobj.get_headers()
print("headers:", headers)
for i in range(dobj.get_num_points()):
s = str(dobj.get_value(headers[0], i))
for header in headers[1:]:
s += "%10.3s" % (dobj.get_value(header, i))
print(s)
print("\n\n\n\nselect_columns")
d = dobj.get_data()
# print("Data:", d)
s = dobj.select_columns(['thing1', 'thing3'])
print("Selected columns:", s)
print("Data range:", analysis.data_range(['thing1', 'thing3'], dobj))
print("Mean:", analysis.mean(['thing1', 'thing3'], dobj))
print("Standard deviation:", analysis.stdev(['thing1', 'thing3'], dobj))
print("Normalize columns separately:",
analysis.normalize_columns_separately(['thing1', 'thing3'], dobj))
print("Normalize columns together:",
analysis.normalize_columns_together(['thing1', 'thing3'], dobj))
def main(argv):
# test command line arguments
if len(argv) < 2:
print('Usage: python %s <csv filename>' % (argv[0]))
exit(0)
# create a data object, which reads in the data
dobj = Data(argv[1])
headers = dobj.get_headers()
#test the five analysis functions
print([headers[0], headers[2]])
print("Data range by column:",
analysis.data_range([headers[0], headers[2]], dobj))
print("Mean:", analysis.mean([headers[0], headers[2]], dobj))
print("Standard deviation:", analysis.stdev([headers[0], headers[2]],
dobj))
print(
"Normalize columns separately:",
analysis.normalize_columns_separately([headers[0], headers[2]], dobj))
print("Normalize columns together:",
analysis.normalize_columns_together([headers[0], headers[2]], dobj))
#Extension 1
print("Median:", analysis.median([headers[0], headers[2]], dobj))
#Extension 2
print("Median Separately:",
analysis.median_separately([headers[0], headers[2]], dobj))
#Extension 3
print("just few rows:", dobj.limit_rows())
#Extension 4
print(
"just a few columns. I changed the limit to 2 for demonstration purposes:",
dobj.limit_columns())
#Extension 5
print("Data range overall:",
analysis.data_range([headers[0], headers[2]], dobj, True))
#Extension 6
print(
"The next two print statements get the last row of data. I add a row of data in between,"
"so they are different.")
print(dobj.get_row(-1))
dobj.add_point([1, 2, 3])
print(dobj.get_row(-1))
def test(filename):
data = Data(filename)
data.addColumn('enumstuff3', 'enum', [
'a', 'a', 'a', 'a', 'a', 'a', 'a', 'a', 'a', 'aa', 'aaa', 'a', 'a',
'a', 'aa'
])
data.addColumn('numberstuff3', 'numeric',
[1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 4, 3, 3, 4, 5])
print(data.get_data())
data.__str__()
print(
an.data_range([data.get_headers()[0],
data.get_headers()[1]], filename))
print(an.mean([data.get_headers()[0], data.get_headers()[1]], filename))
print(an.stdev([data.get_headers()[0], data.get_headers()[1]], filename))
print(
an.normalize_columns_seperately(
[data.get_headers()[0],
data.get_headers()[1]], filename))
print(
an.normalize_columns_together(
[data.get_headers()[0],
data.get_headers()[1]], filename))
print(dobj.numeric_matrix)
# print out the types
print("\nTypes:")
types = dobj.get_types()
s = types[0]
for type in types[1:]:
s += ", " + type
print(s)
r = analysis.data_range(headers, dobj)
print("Data Range:\n ", r)
mean = analysis.mean(headers, dobj)
print("Mean: \n", mean)
std = analysis.stdev(headers, dobj)
print("Standard Deviation: \n", std)
#std = analysis.stdev(headers, dobj)
#print("Standard Deviation: \n", std)
nor_m1 = analysis.normalize_columns_separately(headers, dobj)
print("Normalized Columns Separately: \n", nor_m1)
nor_m2 = analysis.normalize_columns_together(headers, dobj)
print("Normalized Columns Together: \n", nor_m2)
#dobj.add_colummn('new col','numeric', [1,2,3,4,5,6,7,8,9,10,11,12,13,14])
#print("\nAdd new column: 'new col','numeric', [1,2,3,4,5,6,7,8,9,10,11,12,13,14]")
#print("----- New Matrix: -----")
#print(dobj.get_whole_matrix())
# # Load the data files into a Data object
# dataClean = Data(filename='data-clean.csv')
# dataGood = Data(filename='data-good.csv')
# dataNoisy = Data(filename='data-noisy.csv')
#
# # Run multiple linear regression on the Data objects
# analysis.testRegression(dataClean)
# analysis.testRegression(dataGood)
# analysis.testRegression(dataNoisy)
data = Data(filename='GOOG-NASDAQ_TSLA.csv')
# print out some analyses
print("\n\nDescriptive statistics of Tesla's stock data (daily open and close prices and trading volume:")
print("Mean: ", analysis.mean(['Open', 'Close', 'Volume'], data))
print("Standard deviation: ", analysis.stdev(['Open', 'Close', 'Volume'], data))
print("Ranges: ", analysis.dataRange(['Open', 'Close', 'Volume'], data))
print("Normalized columns: ", analysis.normalizeColumnsSeparately(['Open', 'Close', 'Volume'], data))
print("Normalized globally: ", analysis.normalizeColumnsTogether(['Open', 'Close', 'Volume'], data))
print("Variance: ", analysis.variance(['Open', 'Close', 'Volume'], data))
print("Median: ", analysis.median(['Open', 'Close', 'Volume'], data))
print("Mode value: ", analysis.modeValue(['Open', 'Close', 'Volume'], data))
print("Mode frequency: ", analysis.modeFreq(['Open', 'Close', 'Volume'], data))
print("Range value: ", analysis.rangeDiff(['Open', 'Close', 'Volume'], data), "\n")
data.printData(20)
# manipulate the data to show their efficacy
data.set_value(0.0001, 5, 'Open')
data.set_column(data.get_column('Open'), 'Close')
data.add_column(data.get_column('Volume'), 'Volume2', 'numeric')
def main():
numpy.set_printoptions(suppress=True)
print("\n----- Database Info -----")
if len(sys.argv) < 2:
print('Usage: python %s <csv filename>' % (sys.argv[0]))
exit(0)
# create a data object, which reads in the data
dobj = data.Data(sys.argv[1])
print("\nName: ", dobj.get_filename())
# print out information about the dat
print('Number of rows: ', dobj.get_num_points())
print('Number of numeric columns: ', dobj.get_num_dimensions())
# print out the headers
print("\nHeaders:")
headers = dobj.get_headers()
s = headers[0]
for header in headers[1:]:
s += ", " + header
print(s)
# print out the headers
print("\nNumeric Headers:")
nheaders = dobj.get_numericheaders()
s = nheaders[0]
for header in nheaders[1:]:
s += ", " + header
print(s)
# print out the types
print("\nTypes:")
types = dobj.get_types()
s = types[0]
for type in types[1:]:
s += ", " + type
print(s)
r = analysis.data_range(headers, dobj)
print("Data Range:\n ", r)
mean = analysis.mean(headers, dobj)
print("Mean: \n", mean)
std = analysis.stdev(headers, dobj)
print("Standard Deviation: \n", std)
if headers == nheaders:
nor_m1 = analysis.normalize_columns_separately(headers, dobj)
print("Normalized Columns Separately: \n", nor_m1)
if headers == nheaders:
nor_m2 = analysis.normalize_columns_together(headers, dobj)
print("Normalized Columns Together: \n", nor_m2)
s = analysis.sumup(headers, dobj)
print("Sum:\n", s)
print("Variance:\n", analysis.variance(headers, dobj))
# EXTENSION5 ADD COLUMN
dobj.add_colummn('new col', 'numeric',
[1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14])
print(
"\nAdd new column: 'new col','numeric', [1,2,3,4,5,6,7,8,9,10,11,12,13,14]"
)
print("----- New Matrix: -----")
m = dobj.get_whole_matrix()
print(m)
print('Number of rows: ', dobj.get_num_points())
print('Number of numeric columns: ', dobj.get_num_dimensions())
print("---------------------------------")
# EXTENSION6 WRITE TO A CSV file
a = numpy.asarray(m)
with open('foo.csv', 'w') as outputfile:
wr = csv.writer(outputfile, delimiter=',')
wr.writerow(dobj.get_headers())
wr.writerow(dobj.get_types())
for ls in a:
wr.writerow(ls)
