def test_reverse_2(self):
txt = HW1.reverse("spoons")
rtxt = "spoons"
print "If I reverse %s, I get %s. :)" % (rtxt, txt)
tmp = 1
for i in range(len(txt)):
self.assertEqual(txt[i], rtxt[-tmp])
tmp += 1
def test_reverseone(self):
self.assertEqual(HW1.reverse("Test one"), "eno tseT") # basic reversal
def test_reversetwo(self):
self.assertEqual(HW1.reverse("Punctuation test..."), "...tset noitautcnuP")
def test_reversewordsone(self):
self.assertEqual(HW1.reversewords("Test one."), "one Test.")
def test_reversewordstwo(self):
self.assertEqual(HW1.reversewords("Punctuation test..."), "test... Punctuation.")
def test_reversewordlettersone(self):
self.assertEqual(HW1.reversewordletters("This is a test."), "sihT si a tset.")
def test_reversewordletterstwo(self):
self.assertEqual(
HW1.reversewordletters("This sentence has a lot of words."), "sihT ecnetnes sah a tol fo sdrow."
)
def test_shoutone(self):
self.assertEqual(HW1.shout("Hello"), "HELLO!") # One word
def main(targets):
global test_flag
if 'data' in targets:
HW1.main()
if 'test-project' in targets:
beg = time.time()
test_flag = 1
sample_size, categories = HW2.loadConfig("config/test-params.json")
paths = HW2.loadEnv("config/env.json")
HW2.getTestData(categories, sample_size)
smalis = HW2.prepare_data(test_flag)
df, xy = HW2.makeDF(smalis)
train_df, train_y, test_df, test_y = HW2.splitTrain(df, xy)
A_train = HW2.makeA(train_df, train_df["apps"].unique(), df.shape[0])
P_train = HW2.makeP(train_df, df.shape[0])
A_test = HW2.makeA(test_df, test_df["apps"].unique(), df.shape[0])
P_test = HW2.makeP(test_df, df.shape[0])
#y = [i[1] for i in xy]
AAT_train = A_train.dot(
A_train.T) #HW2.matrixply([A_train, A_train.T])
AATest = A_test.dot(A_train.T)
clf = HW2.trainModel(AAT_train, train_y)
preds = HW2.modelPredict(clf, AATest)
HW2.getMetrics(preds, test_y, paths["AA^T"], "AA^T")
APAT_train = A_train.dot(P_train).dot(A_train.T)
APATest = A_test.dot(P_test).dot(A_train.T)
clf = HW2.trainModel(APAT_train, train_y)
preds = HW2.modelPredict(clf, APATest)
HW2.getMetrics(preds, test_y, paths["APA^T"], "APA^T")
B_train = HW2.makeB(train_df, df.shape[0])
B_test = HW2.makeB(test_df, df.shape[0])
ABAT_train = A_train.dot(B_train).dot(A_train.T)
ABATest = A_test.dot(B_test).dot(A_train.T)
clf = HW2.trainModel(ABAT_train, train_y)
preds = HW2.modelPredict(clf, ABATest)
HW2.getMetrics(preds, test_y, paths["ABA^T"], "ABA^T")
APBPTAT_train = A_train.dot(P_train).dot(B_train).dot(P_train.T).dot(
A_train.T)
APBPTATest = A_test.dot(P_test).dot(B_test).dot(P_train.T).dot(
A_train.T)
clf = HW2.trainModel(APBPTAT_train, train_y)
preds = HW2.modelPredict(clf, APBPTATest)
HW2.getMetrics(preds, test_y, paths["APBP^TA^T"], "APBP^TA^T")
if 'process' in targets:
#cleans and prepares the data for analysis
#smalis = getAllSmaliFiles("Apps")
print(test_flag)
smalis = HW2.prepare_data(test_flag)
x, y = HW2.makeBaselineFeatures(smalis)
HW2.baseline(x, y)
return
def test_convertions():
assert HW1.arabic_to_roman(100) == "C"
assert HW1.arabic_to_roman(3999) == "MMMCMXCIX"
assert HW1.arabic_to_roman(893) == "DCCCXCIII"
assert HW1.arabic_to_roman(12) == "XII"
assert HW1.arabic_to_roman(1213) == "MCCXIII"
assert HW1.arabic_to_roman(432) == "CDXXXII"
assert HW1.arabic_to_roman(932) == "CMXXXII"
assert HW1.arabic_to_roman(1001) == "MI"
assert HW1.arabic_to_roman(384) == "CCCLXXXIV"
def main():
u_range = [-1, 1]
v_range = [-1, 1]
N = 100
x, y, f = generate_x_f_y(N, u_range, v_range)
HW1.plot_a_line_2D(f, u_range, v_range)
HW1.scatterplot(x, y)
g = linear_regression_algorithm(x, y)
HW1.plot_a_line_2D(g, u_range, v_range)
E_in = evaluate_E(x, y, g)
print(E_in)
g_pla, numberOfIteration = pla_combine_linear_regression(x, y)
print(numberOfIteration)
def generate_random_x(N=100, u_range=[-1, 1], v_range=[-1, 1]):
"""
Generate a set of N random points in the specified ranges
Inputs
------
- N: number of points
- u_range: horizontal range
- v_range: vertival range
Outputs
------
- x: 2D array where the rows has length 3 which represents the locations of
a data point with the first one is set to 1, and the columns is the
number of data points considered
"""
x = HW1.generate_random_points(N, u_range, v_range)
x_vec = np.vstack((np.ones(N), x))
return x_vec
def test1_NextDay(self):
result= HW1.NextDay((23, 6, 2017))
self.assertEqual('24/6/2017', result)
def test1_Value(self):
result = HW1.Value(7145)
self.assertEqual(11, result)
def stest_shoutfive(self):
self.assertEqual(
HW1.shout("Multiple periods..."), "MULTIPLE PERIODS!!!"
) # turn punctuation into exclaimation =
def test_shoutthree(self):
self.assertEqual(HW1.shout("Exclaimed Hello!!!"), "EXCLAIMED HELLO!!!!") # Punctuation
def test_errors():
assert HW1.arabic_to_roman("100") == "ERROR"
assert HW1.arabic_to_roman(100.123) == "ERROR"
assert HW1.arabic_to_roman("test") == "ERROR"
assert HW1.arabic_to_roman(100.00) == "ERROR"
def test3_Value(self):
result = HW1.Value(351)
self.assertEqual(8, result)
def test2_IsPrimary(self):
result = HW1.IsPrimary(21)
self.assertEqual(False, result)
def test1_IsPrimary(self):
result = HW1.IsPrimary(23)
self.assertEqual(True, result)
def test2_NextDay(self):
result = HW1.NextDay((28, 2, 2012))
self.assertEqual('29/2/2012', result)
def test2_Reduce(self):
result = HW1.Reduce(1020034000)
self.assertEqual(1234, result)
def test1_Reduce(self):
result = HW1.Reduce(-160760)
self.assertEqual(-1676, result)
def test3_Pascal(self):
result = HW1.Pascal(5, 3)
self.assertEqual(10, result)
def test2_GoodOrder(self):
result = HW1.GoodOrder(264)
self.assertEqual(True, result)
def test2_Pascal(self):
result = HW1.Pascal(10, 4)
self.assertEqual(210, result)
def test_shout2(self):
self.assertEqual(HW1.shout("BLAH"), "BLAH!")
def test_shout3(self):
self.assertEqual(HW1.shout("Blah!"), "BLAH!")
def test_shout4(self):
self.assertEqual(HW1.shout("Hey. You!"), "HEY! YOU!")
def pla_combine_linear_regression(x, y):
w_initial = linear_regression_algorithm(x, y)
g, numberOfIteration = HW1.pla_algorithm(x, y, w=w_initial)
return g, numberOfIteration
def test_shout_question(self):
self.assertEqual(HW1.shout("Hello world?"), "HELLO WORLD!")
def test_shouttwo(self):
self.assertEqual(HW1.shout("Hello again"), "HELLO AGAIN!") # Sentence
def test_reversewords_string(self):
self.assertEqual(HW1.reversewords("Hello world."), "world Hello.")
def test_shoutfour(self):
self.assertEqual(HW1.shout("CAPS?"), "CAPS!!") # Already in caps, add a different punctuation
def test_reversewordletters_string(self):
self.assertEqual(HW1.reversewordletters("A civic testset is nice."), "A civic testset si ecin.")
def test2_Value(self):
result = HW1.Value(15)
self.assertEqual(7, result)
def test_piglatin_sentence(self):
self.assertEqual(HW1.piglatin("Romans like bacon."), "omansre ikele aconbe")
def test1_Figure(self):
result= HW1.Figure(7)
expected = [' 1 ', ' 2 2 ', ' 3 3 ', ' 4 4 ', ' 5 5 ', ' 6 6 ', '7654321234567']
self.assertEqual(expected,result)
def test_shout_with_nums(self):
self.assertEqual(HW1.shout("I like the number 7."), "I LIKE THE NUMBER 7!")
def test3_GoodOrder(self):
result = HW1.GoodOrder(1573)
self.assertEqual(True, result)
def test1_GoodOrder(self):
result = HW1.GoodOrder(12345)
self.assertEqual(False, result)
def test_reverse1(self):
self.assertEqual(HW1.reverse("asdf blah"), "halb fdsa")
def test1_Pascal(self):
result = HW1.Pascal(3, 2)
self.assertEqual(3, result)
def test_reverse_string(self):
self.assertEqual(HW1.reverse("Bom bard a drab mob."), ".bom bard a drab moB")
def test_reversewords1(self):
self.assertEqual(HW1.reversewords("Hi, my name is Blah."), "Blah is name my, Hi.")
def test_reversewords_2sentence(self):
self.assertEqual(HW1.reversewords("Hello world. What's your name?"), "world Hello. name your What's.")
def test_reversewordletters1(self):
self.assertEqual(HW1.reversewordletters("Hi, my name is Blah."), "iH, ym, eman, si, halB")
def test_piglatin_sentence(self): # preserving old test case
self.assertEqual(HW1.piglatin("pig latin"), "igpe atinle")
def test_piglatin1(self):
self.assertEqual(HW1.piglatin("nix"), "ixnay")
def test_palindrome_sentence(self):
self.assertEqual(HW1.reverse("Bom bard a drab mob."), ".bom bard a drab moB")
def test_shout1(self):
self.assertEqual(HW1.shout("Hey there"), "HEY THERE!")
def test_no_punctuation_rwl(self):
self.assertEqual(HW1.reversewordletters("A long string without punctuation"), "A gnol gnirts tuohtiw noitautcnup")
# In[34]:
groupA = merge_AB_under.loc[merge_AB_under['plan_type_low_uae_no_trial'] ==
0] #14 day trial
groupB = merge_AB_under.loc[merge_AB_under['plan_type_low_uae_no_trial'] == 1]
# In[35]:
A_list = list(groupA['current_sub_TF'])
B_list = list(groupB['current_sub_TF'])
# In[36]:
import scipy
norm = scipy.stats.norm()
ABTesting.t_test(A_list, B_list, 0.95)
# B>A. It means that current subscribers with low uae no trail are more than ones with base uae 14 day trail. The difference is statistically significant.
# ## PART III. Customer Segmentation
# In[37]:
import pandas as pd
import datetime
import numpy as np
import matplotlib.pyplot as plt
import numpy
import seaborn as sns
# In[38]:
