adding all files done so far

bayes-learning/class.py

@@ -0,0 +1,42 @@
+import pandas as pd
+import os
+
+# path = os.getcwd()
+
+# data = pd.read_csv(path + str('/data/Social_Network_Ads.csv'),
+#                    engine='python')
+# df = pd.DataFrame(data)
+
+
+# train_size = int(0.75 * df.shape[0])
+# test_size = int(0.25 * df.shape[0])
+
+# print('Training set size {}, Testing set size {}'.format(train_size,
+#                                                          test_size))
+
+
+class bayesClassifer(object):
+    """initial implmentation of a bayes classifer"""
+
+    path = os.getcwd()
+
+    def __init__(self, data_file):
+        super(bayesClassifer, self).__init__()
+        self.data_file = data_file
+
+    def createDataFrame(self):
+        return pd.read_csv(self.path + self.data_file, engine='python')
+
+    def print_debug(self):
+        print('{0} rows, {1} columns'.format(self.df.shape[0],
+              self.df.shape[1]))
+        print(self.df[1:7])
+
+    def trainData(dataframe):
+        train_size = int(0.75 * dataframe.shape[0])
+        test_size = int(0.25 * dataframe.shape[0])
+        return(train_size, test_size)
+
+
+bayesClassifer('/data/Social_Network_Ads.csv')
+bayesClassifer.createDataFrame()

bayes-learning/data/Social_Network_Ads.csv

@@ -0,0 +1,401 @@
+User ID,Gender,Age,EstimatedSalary,Purchased
+15624510,Male,19,19000,0
+15810944,Male,35,20000,0
+15668575,Female,26,43000,0
+15603246,Female,27,57000,0
+15804002,Male,19,76000,0
+15728773,Male,27,58000,0
+15598044,Female,27,84000,0
+15694829,Female,32,150000,1
+15600575,Male,25,33000,0
+15727311,Female,35,65000,0
+15570769,Female,26,80000,0
+15606274,Female,26,52000,0
+15746139,Male,20,86000,0
+15704987,Male,32,18000,0
+15628972,Male,18,82000,0
+15697686,Male,29,80000,0
+15733883,Male,47,25000,1
+15617482,Male,45,26000,1
+15704583,Male,46,28000,1
+15621083,Female,48,29000,1
+15649487,Male,45,22000,1
+15736760,Female,47,49000,1
+15714658,Male,48,41000,1
+15599081,Female,45,22000,1
+15705113,Male,46,23000,1
+15631159,Male,47,20000,1
+15792818,Male,49,28000,1
+15633531,Female,47,30000,1
+15744529,Male,29,43000,0
+15669656,Male,31,18000,0
+15581198,Male,31,74000,0
+15729054,Female,27,137000,1
+15573452,Female,21,16000,0
+15776733,Female,28,44000,0
+15724858,Male,27,90000,0
+15713144,Male,35,27000,0
+15690188,Female,33,28000,0
+15689425,Male,30,49000,0
+15671766,Female,26,72000,0
+15782806,Female,27,31000,0
+15764419,Female,27,17000,0
+15591915,Female,33,51000,0
+15772798,Male,35,108000,0
+15792008,Male,30,15000,0
+15715541,Female,28,84000,0
+15639277,Male,23,20000,0
+15798850,Male,25,79000,0
+15776348,Female,27,54000,0
+15727696,Male,30,135000,1
+15793813,Female,31,89000,0
+15694395,Female,24,32000,0
+15764195,Female,18,44000,0
+15744919,Female,29,83000,0
+15671655,Female,35,23000,0
+15654901,Female,27,58000,0
+15649136,Female,24,55000,0
+15775562,Female,23,48000,0
+15807481,Male,28,79000,0
+15642885,Male,22,18000,0
+15789109,Female,32,117000,0
+15814004,Male,27,20000,0
+15673619,Male,25,87000,0
+15595135,Female,23,66000,0
+15583681,Male,32,120000,1
+15605000,Female,59,83000,0
+15718071,Male,24,58000,0
+15679760,Male,24,19000,0
+15654574,Female,23,82000,0
+15577178,Female,22,63000,0
+15595324,Female,31,68000,0
+15756932,Male,25,80000,0
+15726358,Female,24,27000,0
+15595228,Female,20,23000,0
+15782530,Female,33,113000,0
+15592877,Male,32,18000,0
+15651983,Male,34,112000,1
+15746737,Male,18,52000,0
+15774179,Female,22,27000,0
+15667265,Female,28,87000,0
+15655123,Female,26,17000,0
+15595917,Male,30,80000,0
+15668385,Male,39,42000,0
+15709476,Male,20,49000,0
+15711218,Male,35,88000,0
+15798659,Female,30,62000,0
+15663939,Female,31,118000,1
+15694946,Male,24,55000,0
+15631912,Female,28,85000,0
+15768816,Male,26,81000,0
+15682268,Male,35,50000,0
+15684801,Male,22,81000,0
+15636428,Female,30,116000,0
+15809823,Male,26,15000,0
+15699284,Female,29,28000,0
+15786993,Female,29,83000,0
+15709441,Female,35,44000,0
+15710257,Female,35,25000,0
+15582492,Male,28,123000,1
+15575694,Male,35,73000,0
+15756820,Female,28,37000,0
+15766289,Male,27,88000,0
+15593014,Male,28,59000,0
+15584545,Female,32,86000,0
+15675949,Female,33,149000,1
+15672091,Female,19,21000,0
+15801658,Male,21,72000,0
+15706185,Female,26,35000,0
+15789863,Male,27,89000,0
+15720943,Male,26,86000,0
+15697997,Female,38,80000,0
+15665416,Female,39,71000,0
+15660200,Female,37,71000,0
+15619653,Male,38,61000,0
+15773447,Male,37,55000,0
+15739160,Male,42,80000,0
+15689237,Male,40,57000,0
+15679297,Male,35,75000,0
+15591433,Male,36,52000,0
+15642725,Male,40,59000,0
+15701962,Male,41,59000,0
+15811613,Female,36,75000,0
+15741049,Male,37,72000,0
+15724423,Female,40,75000,0
+15574305,Male,35,53000,0
+15678168,Female,41,51000,0
+15697020,Female,39,61000,0
+15610801,Male,42,65000,0
+15745232,Male,26,32000,0
+15722758,Male,30,17000,0
+15792102,Female,26,84000,0
+15675185,Male,31,58000,0
+15801247,Male,33,31000,0
+15725660,Male,30,87000,0
+15638963,Female,21,68000,0
+15800061,Female,28,55000,0
+15578006,Male,23,63000,0
+15668504,Female,20,82000,0
+15687491,Male,30,107000,1
+15610403,Female,28,59000,0
+15741094,Male,19,25000,0
+15807909,Male,19,85000,0
+15666141,Female,18,68000,0
+15617134,Male,35,59000,0
+15783029,Male,30,89000,0
+15622833,Female,34,25000,0
+15746422,Female,24,89000,0
+15750839,Female,27,96000,1
+15749130,Female,41,30000,0
+15779862,Male,29,61000,0
+15767871,Male,20,74000,0
+15679651,Female,26,15000,0
+15576219,Male,41,45000,0
+15699247,Male,31,76000,0
+15619087,Female,36,50000,0
+15605327,Male,40,47000,0
+15610140,Female,31,15000,0
+15791174,Male,46,59000,0
+15602373,Male,29,75000,0
+15762605,Male,26,30000,0
+15598840,Female,32,135000,1
+15744279,Male,32,100000,1
+15670619,Male,25,90000,0
+15599533,Female,37,33000,0
+15757837,Male,35,38000,0
+15697574,Female,33,69000,0
+15578738,Female,18,86000,0
+15762228,Female,22,55000,0
+15614827,Female,35,71000,0
+15789815,Male,29,148000,1
+15579781,Female,29,47000,0
+15587013,Male,21,88000,0
+15570932,Male,34,115000,0
+15794661,Female,26,118000,0
+15581654,Female,34,43000,0
+15644296,Female,34,72000,0
+15614420,Female,23,28000,0
+15609653,Female,35,47000,0
+15594577,Male,25,22000,0
+15584114,Male,24,23000,0
+15673367,Female,31,34000,0
+15685576,Male,26,16000,0
+15774727,Female,31,71000,0
+15694288,Female,32,117000,1
+15603319,Male,33,43000,0
+15759066,Female,33,60000,0
+15814816,Male,31,66000,0
+15724402,Female,20,82000,0
+15571059,Female,33,41000,0
+15674206,Male,35,72000,0
+15715160,Male,28,32000,0
+15730448,Male,24,84000,0
+15662067,Female,19,26000,0
+15779581,Male,29,43000,0
+15662901,Male,19,70000,0
+15689751,Male,28,89000,0
+15667742,Male,34,43000,0
+15738448,Female,30,79000,0
+15680243,Female,20,36000,0
+15745083,Male,26,80000,0
+15708228,Male,35,22000,0
+15628523,Male,35,39000,0
+15708196,Male,49,74000,0
+15735549,Female,39,134000,1
+15809347,Female,41,71000,0
+15660866,Female,58,101000,1
+15766609,Female,47,47000,0
+15654230,Female,55,130000,1
+15794566,Female,52,114000,0
+15800890,Female,40,142000,1
+15697424,Female,46,22000,0
+15724536,Female,48,96000,1
+15735878,Male,52,150000,1
+15707596,Female,59,42000,0
+15657163,Male,35,58000,0
+15622478,Male,47,43000,0
+15779529,Female,60,108000,1
+15636023,Male,49,65000,0
+15582066,Male,40,78000,0
+15666675,Female,46,96000,0
+15732987,Male,59,143000,1
+15789432,Female,41,80000,0
+15663161,Male,35,91000,1
+15694879,Male,37,144000,1
+15593715,Male,60,102000,1
+15575002,Female,35,60000,0
+15622171,Male,37,53000,0
+15795224,Female,36,126000,1
+15685346,Male,56,133000,1
+15691808,Female,40,72000,0
+15721007,Female,42,80000,1
+15794253,Female,35,147000,1
+15694453,Male,39,42000,0
+15813113,Male,40,107000,1
+15614187,Male,49,86000,1
+15619407,Female,38,112000,0
+15646227,Male,46,79000,1
+15660541,Male,40,57000,0
+15753874,Female,37,80000,0
+15617877,Female,46,82000,0
+15772073,Female,53,143000,1
+15701537,Male,42,149000,1
+15736228,Male,38,59000,0
+15780572,Female,50,88000,1
+15769596,Female,56,104000,1
+15586996,Female,41,72000,0
+15722061,Female,51,146000,1
+15638003,Female,35,50000,0
+15775590,Female,57,122000,1
+15730688,Male,41,52000,0
+15753102,Female,35,97000,1
+15810075,Female,44,39000,0
+15723373,Male,37,52000,0
+15795298,Female,48,134000,1
+15584320,Female,37,146000,1
+15724161,Female,50,44000,0
+15750056,Female,52,90000,1
+15609637,Female,41,72000,0
+15794493,Male,40,57000,0
+15569641,Female,58,95000,1
+15815236,Female,45,131000,1
+15811177,Female,35,77000,0
+15680587,Male,36,144000,1
+15672821,Female,55,125000,1
+15767681,Female,35,72000,0
+15600379,Male,48,90000,1
+15801336,Female,42,108000,1
+15721592,Male,40,75000,0
+15581282,Male,37,74000,0
+15746203,Female,47,144000,1
+15583137,Male,40,61000,0
+15680752,Female,43,133000,0
+15688172,Female,59,76000,1
+15791373,Male,60,42000,1
+15589449,Male,39,106000,1
+15692819,Female,57,26000,1
+15727467,Male,57,74000,1
+15734312,Male,38,71000,0
+15764604,Male,49,88000,1
+15613014,Female,52,38000,1
+15759684,Female,50,36000,1
+15609669,Female,59,88000,1
+15685536,Male,35,61000,0
+15750447,Male,37,70000,1
+15663249,Female,52,21000,1
+15638646,Male,48,141000,0
+15734161,Female,37,93000,1
+15631070,Female,37,62000,0
+15761950,Female,48,138000,1
+15649668,Male,41,79000,0
+15713912,Female,37,78000,1
+15586757,Male,39,134000,1
+15596522,Male,49,89000,1
+15625395,Male,55,39000,1
+15760570,Male,37,77000,0
+15566689,Female,35,57000,0
+15725794,Female,36,63000,0
+15673539,Male,42,73000,1
+15705298,Female,43,112000,1
+15675791,Male,45,79000,0
+15747043,Male,46,117000,1
+15736397,Female,58,38000,1
+15678201,Male,48,74000,1
+15720745,Female,37,137000,1
+15637593,Male,37,79000,1
+15598070,Female,40,60000,0
+15787550,Male,42,54000,0
+15603942,Female,51,134000,0
+15733973,Female,47,113000,1
+15596761,Male,36,125000,1
+15652400,Female,38,50000,0
+15717893,Female,42,70000,0
+15622585,Male,39,96000,1
+15733964,Female,38,50000,0
+15753861,Female,49,141000,1
+15747097,Female,39,79000,0
+15594762,Female,39,75000,1
+15667417,Female,54,104000,1
+15684861,Male,35,55000,0
+15742204,Male,45,32000,1
+15623502,Male,36,60000,0
+15774872,Female,52,138000,1
+15611191,Female,53,82000,1
+15674331,Male,41,52000,0
+15619465,Female,48,30000,1
+15575247,Female,48,131000,1
+15695679,Female,41,60000,0
+15713463,Male,41,72000,0
+15785170,Female,42,75000,0
+15796351,Male,36,118000,1
+15639576,Female,47,107000,1
+15693264,Male,38,51000,0
+15589715,Female,48,119000,1
+15769902,Male,42,65000,0
+15587177,Male,40,65000,0
+15814553,Male,57,60000,1
+15601550,Female,36,54000,0
+15664907,Male,58,144000,1
+15612465,Male,35,79000,0
+15810800,Female,38,55000,0
+15665760,Male,39,122000,1
+15588080,Female,53,104000,1
+15776844,Male,35,75000,0
+15717560,Female,38,65000,0
+15629739,Female,47,51000,1
+15729908,Male,47,105000,1
+15716781,Female,41,63000,0
+15646936,Male,53,72000,1
+15768151,Female,54,108000,1
+15579212,Male,39,77000,0
+15721835,Male,38,61000,0
+15800515,Female,38,113000,1
+15591279,Male,37,75000,0
+15587419,Female,42,90000,1
+15750335,Female,37,57000,0
+15699619,Male,36,99000,1
+15606472,Male,60,34000,1
+15778368,Male,54,70000,1
+15671387,Female,41,72000,0
+15573926,Male,40,71000,1
+15709183,Male,42,54000,0
+15577514,Male,43,129000,1
+15778830,Female,53,34000,1
+15768072,Female,47,50000,1
+15768293,Female,42,79000,0
+15654456,Male,42,104000,1
+15807525,Female,59,29000,1
+15574372,Female,58,47000,1
+15671249,Male,46,88000,1
+15779744,Male,38,71000,0
+15624755,Female,54,26000,1
+15611430,Female,60,46000,1
+15774744,Male,60,83000,1
+15629885,Female,39,73000,0
+15708791,Male,59,130000,1
+15793890,Female,37,80000,0
+15646091,Female,46,32000,1
+15596984,Female,46,74000,0
+15800215,Female,42,53000,0
+15577806,Male,41,87000,1
+15749381,Female,58,23000,1
+15683758,Male,42,64000,0
+15670615,Male,48,33000,1
+15715622,Female,44,139000,1
+15707634,Male,49,28000,1
+15806901,Female,57,33000,1
+15775335,Male,56,60000,1
+15724150,Female,49,39000,1
+15627220,Male,39,71000,0
+15672330,Male,47,34000,1
+15668521,Female,48,35000,1
+15807837,Male,48,33000,1
+15592570,Male,47,23000,1
+15748589,Female,45,45000,1
+15635893,Male,60,42000,1
+15757632,Female,39,59000,0
+15691863,Female,46,41000,1
+15706071,Male,51,23000,1
+15654296,Female,50,20000,1
+15755018,Male,36,33000,0
+15594041,Female,49,36000,1

bayes-learning/lesson1-rewrite.py

@@ -0,0 +1,33 @@
+import pandas as pd
+import os
+from sklearn.preprocessing import StandardScaler
+from matplotlib.colors import ListedColormap
+import numpy as np
+import matplotlib
+import matplotlib.pyplot as plt
+
+matplotlib.rcParams['backend'] = 'TkAgg'
+
+
+class getData(object):
+    """docstring for getData"""
+    def __init__(self, file):
+        super(getData, self).__init__()
+        self.file = file
+
+
+class Bayes(getData):
+    """docstring for Bayes"""
+
+    def __init__(self, file):
+        super(Bayes, self).__init__()
+        self.file = file
+
+    def get_path(self):
+        path = os.getcwd()
+        file_path = path + self.file
+        return file_path
+
+
+bayes = Bayes(file='data/Social_Network_Ads.csv')
+print(bayes.get_path())

bayes-learning/lesson1.py

@@ -0,0 +1,152 @@
+import pandas as pd
+import os
+from sklearn.preprocessing import Normalizer, StandardScaler
+from matplotlib.colors import ListedColormap
+import numpy as np
+import matplotlib
+import matplotlib.pyplot as plt
+from sklearn.naive_bayes import GaussianNB
+from sklearn.metrics import confusion_matrix, classification_report
+
+matplotlib.rcParams['backend'] = 'TkAgg'
+
+plt.style.use('seaborn-dark-palette')
+
+# path = os.getcwd()
+path = '/home/dtomlinson/projects/bayes-learning'
+
+data = pd.read_csv(path + str('/data/Social_Network_Ads.csv'), engine='python')
+df = pd.DataFrame(data)
+
+print('{0} rows, {1} columns'.format(df.shape[0], df.shape[1]))
+# print(df[1:7])
+
+train_size = int(0.75 * df.shape[0])
+test_size = int(0.25 * df.shape[0])
+
+print('Training set size {}, Testing set size {}'.format(train_size,
+                                                         test_size))
+
+df = df.sample(frac=1).reset_index(drop=True)
+
+print(df[0:5])
+
+X = df.iloc[:, [2, 3]].values
+y = df.iloc[:, 4].values
+
+normalizer = StandardScaler(copy=False).fit(X)
+X = normalizer.fit_transform(X)
+
+X_train = X[0:train_size, :]
+y_train = y[0:train_size]
+
+X_test = X[train_size:, :]
+y_test = y[train_size:]
+
+X_set, y_set = X_train, y_train
+
+
+# ind = np.argsort(X_set[:, 0])
+# X_set = X_set[ind]
+
+
+for i, j in enumerate(np.unique(y_set)):
+    plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
+                c=ListedColormap(('red', 'blue'))(i),
+                label=j, marker='.')
+
+
+plt.title('Training Set')
+plt.xlabel('Age')
+plt.ylabel('Estimated Salary')
+plt.legend()
+
+
+def generate_data(class_data_dic, X_train, y_train):
+
+    first_one = True
+    first_zero = True
+
+    for i in range(y_train.shape[0]):
+        X_temp = X_train[i, :].reshape(X_train[i, :].shape[0], 1)
+
+        if y_train[i] == 1:
+            if first_one is True:
+                class_data_dic[1] = X_temp
+                first_one = False
+            else:
+                class_data_dic[1] = np.append(class_data_dic[1], X_temp,
+                                              axis=1)
+        elif y_train[i] == 0:
+            if first_zero is True:
+                class_data_dic[0] = X_temp
+                first_zero = False
+            else:
+                class_data_dic[0] = np.append(class_data_dic[0], X_temp,
+                                              axis=1)
+
+    return class_data_dic
+
+
+class_data_dic = generate_data(class_data_dic={}, X_train=X_train,
+                               y_train=y_train)
+
+"""find the mean (2x1) for each column. 0 and 1 are the values for having 0
+and 1 seperately"""
+
+mean_0 = np.mean(class_data_dic[0], axis=1)
+mean_1 = np.mean(class_data_dic[1], axis=1)
+std_0 = np.std(class_data_dic[0], axis=1)
+std_1 = np.std(class_data_dic[1], axis=1)
+
+print('mean_0={}, std_0={}, mean_1={}, std_1={}'.format(
+    mean_0, mean_1, std_0, std_1))
+# plt.show()
+
+"""define the likelyhood function (the pdf of the norm dist) """
+
+
+def likelyhood(x, mean, sigma):
+    return np.exp(-(x - mean)**2 / (2 * sigma ** 2)) * (1 / (np.sqrt(2 * np.pi) * sigma ** 2))
+
+
+""" the posterior function times together all the likelihoods for each row
+of X_test here we are working out the likelihood func for each row of X_test
+with their corresponding mean and stdev """
+"""we then times this by the prior-prob-func to find the posterior func"""
+
+
+def posterior(X, X_train_class, mean_, std_):
+    product = np.prod(likelyhood(X, mean_, std_), axis=1)
+    product = product * (X_train_class.shape[0] / X.shape[0])
+    return product
+
+
+""" we test the posterior fun with the test data to find the probs"""
+p_1 = posterior(X_test, class_data_dic[1], mean_1, std_1)
+p_0 = posterior(X_test, class_data_dic[0], mean_0, std_0)
+y_pred = 1 * (p_1 > p_0)
+
+print(X_test.shape)
+print(class_data_dic[0].shape)
+print(p_1.shape)
+tp = len([i for i in range(0, y_test.shape[0])
+          if y_test[i] == 0 and y_pred[i] == 0])
+tn = len([i for i in range(0, y_test.shape[0])
+          if y_test[i] == 0 and y_pred[i] == 1])
+fp = len([i for i in range(0, y_test.shape[0])
+          if y_test[i] == 1 and y_pred[i] == 0])
+fn = len([i for i in range(0, y_test.shape[0])
+          if y_test[i] == 1 and y_pred[i] == 1])
+confusion_matrix_alg = np.array([[tp, tn], [fp, fn]])
+print(confusion_matrix_alg)
+
+
+classifer = GaussianNB()
+classifer.fit(X_train, y_train)
+
+y_pred = classifer.predict(X_test)
+cm = confusion_matrix(y_test, y_pred)
+report = classification_report(y_test, y_pred)
+print(cm)
+print(report)

bayes-learning/output.csv

@@ -0,0 +1,3 @@
+,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190
+0,-0.06256109973954335,-1.1132055228463764,-0.25358735848624026,-0.06256109973954335,0.22397828838050202,-0.4446136172329372,0.3194914177538505,0.12846515900715358,-0.15807422911289182,-0.34910048785958875,1.083596452740638,-0.25358735848624026,-0.7311530053529826,-0.4446136172329372,-0.25358735848624026,-0.15807422911289182,-1.3042317815930733,-1.7817974284598157,-0.7311530053529826,-0.7311530053529826,0.7970570646205928,-1.2087186522197249,-1.3997449109664217,-0.7311530053529826,-1.7817974284598157,-0.25358735848624026,-0.34910048785958875,0.415004547127199,-0.06256109973954335,-1.1132055228463764,-1.6862842990864673,-0.25358735848624026,-1.3997449109664217,-0.06256109973954335,-0.9221792640996795,-0.6356398759796341,-0.826666134726331,0.12846515900715358,0.22397828838050202,-0.06256109973954335,-0.6356398759796341,-0.6356398759796341,-0.826666134726331,0.3194914177538505,0.5105176765005474,-1.3997449109664217,-1.3042317815930733,-1.3042317815930733,-0.25358735848624026,-0.9221792640996795,-0.15807422911289182,-1.017692393473028,-0.826666134726331,-0.4446136172329372,-0.5401267466062857,-1.1132055228463764,-0.25358735848624026,-1.1132055228463764,-0.9221792640996795,-1.017692393473028,0.03295202963380511,-0.4446136172329372,-1.017692393473028,-1.2087186522197249,0.12846515900715358,0.415004547127199,-0.25358735848624026,-1.017692393473028,-0.25358735848624026,0.3194914177538505,-1.4952580403397702,-1.017692393473028,0.3194914177538505,1.1791095821139865,-0.5401267466062857,0.9880833233672897,-0.826666134726331,-1.1132055228463764,-1.8773105578331641,0.03295202963380511,-0.9221792640996795,-1.5907711697131186,-1.5907711697131186,2.0387277464741227,0.3194914177538505,-1.1132055228463764,-1.4952580403397702,1.083596452740638,-0.826666134726331,-1.5907711697131186,-0.6356398759796341,-1.8773105578331641,-0.7311530053529826,0.03295202963380511,-0.25358735848624026,-1.7817974284598157,-0.7311530053529826,-1.017692393473028,-0.06256109973954335,-0.25358735848624026,-0.5401267466062857,1.3701358408606836,-0.6356398759796341,0.22397828838050202,-0.06256109973954335,-1.2087186522197249,0.03295202963380511,-0.4446136172329372,0.7970570646205928,-1.017692393473028,-0.6356398759796341,-0.4446136172329372,-0.6356398759796341,0.03295202963380511,0.22397828838050202,0.22397828838050202,-1.6862842990864673,-1.1132055228463764,0.8925701939939412,-1.017692393473028,0.12846515900715358,-0.15807422911289182,0.22397828838050202,0.12846515900715358,-0.6356398759796341,-0.9221792640996795,-0.06256109973954335,-0.25358735848624026,-0.826666134726331,0.03295202963380511,-0.25358735848624026,-1.2087186522197249,-0.25358735848624026,0.3194914177538505,-1.1132055228463764,-0.25358735848624026,-1.017692393473028,-1.1132055228463764,-0.25358735848624026,-0.25358735848624026,-0.06256109973954335,-1.7817974284598157,-0.4446136172329372,-1.6862842990864673,-1.8773105578331641,-0.25358735848624026,-1.7817974284598157,-1.3997449109664217,-1.1132055228463764,0.415004547127199,0.12846515900715358,-0.25358735848624026,-1.3042317815930733,-1.3997449109664217,-0.06256109973954335,-0.34910048785958875,0.415004547127199,-0.25358735848624026,-1.2087186522197249,-0.25358735848624026,-0.15807422911289182,0.3194914177538505,-1.1132055228463764,-1.7817974284598157,-1.3042317815930733,-0.9221792640996795,-1.5907711697131186,0.03295202963380511,0.03295202963380511,-1.3042317815930733,-0.25358735848624026,-0.15807422911289182,-0.9221792640996795,0.415004547127199,-1.6862842990864673,-1.1132055228463764,-0.7311530053529826,-0.25358735848624026,0.03295202963380511,-0.9221792640996795,-0.25358735848624026,0.3194914177538505,-0.25358735848624026,-0.06256109973954335,0.3194914177538505,-1.017692393473028,-1.3042317815930733,0.22397828838050202,-0.7311530053529826,-1.3042317815930733,0.415004547127199
+1,-0.5210059679415002,-1.0202085298693855,-0.25672225868556103,-0.49164111135750704,0.1543857334903445,-0.28608711526955427,0.06629116373836477,-0.25672225868556103,-0.5797356811094868,1.3289799968500746,0.12502087690635127,-0.28608711526955427,-0.60910053769348,-0.8440193903654261,-0.3154519718535475,-0.1979925455175745,-1.2551273825413316,0.44803429933027705,-0.22735740210156777,1.3583448534340679,0.3599397295782973,0.5067640124982635,-0.6384653942774733,0.5067640124982635,-1.4900462352132775,0.21311544665833101,-0.7852896771974396,-0.139262832349588,0.12502087690635127,0.3012100164103108,0.12502087690635127,-0.4329113981895205,-1.2257625259573384,-0.22735740210156777,-0.961478816701399,-1.0495733864533787,-0.7852896771974396,-0.3154519718535475,-0.37418168502153404,0.1543857334903445,0.12502087690635127,-0.10989797576559475,0.1543857334903445,0.06629116373836477,1.8575474153619531,-0.1979925455175745,0.56549372566625,-1.3725868088773046,-1.3725868088773046,0.56549372566625,-0.46227625477351375,-1.1376679562053587,-0.7852896771974396,1.2702502836820881,0.4773991559142703,0.4773991559142703,0.036926307154371514,-1.1083030996213654,-0.7559248206134463,-0.34481682843754075,1.240885427098095,-1.1376679562053587,-0.34481682843754075,0.3012100164103108,0.036926307154371514,0.3012100164103108,0.09565602032235802,-1.4606813786292843,0.06629116373836477,-0.5210059679415002,0.33057487299430405,0.56549372566625,-0.5210059679415002,-0.7559248206134463,1.387709710018061,2.092466268033899,-0.25672225868556103,0.33057487299430405,0.4773991559142703,-0.25672225868556103,0.2718451598263175,0.5361288690822568,-0.05116826259760824,0.3893045861622905,0.2718451598263175,-1.167032812789352,-0.1979925455175745,-0.139262832349588,0.3893045861622905,-1.5781408049652574,-1.6075056615492507,-0.7559248206134463,0.3012100164103108,-0.5797356811094868,-1.2551273825413316,0.18375059007433778,0.2718451598263175,0.4186694427462838,0.3012100164103108,-0.9027491035334125,-1.519411091797271,1.2996151402660814,-0.05116826259760824,0.24248030324232428,0.036926307154371514,-1.4019516654612978,-0.5797356811094868,-1.2257625259573384,0.7710477217542028,-0.37418168502153404,-0.34481682843754075,-0.02180340601361499,0.18375059007433778,0.036926307154371514,0.1543857334903445,-0.139262832349588,-0.60910053769348,0.3012100164103108,-0.6678302508614665,0.5948585822502434,0.2718451598263175,-0.28608711526955427,0.06629116373836477,0.09565602032235802,0.56549372566625,0.44803429933027705,0.21311544665833101,-0.7559248206134463,0.3012100164103108,0.036926307154371514,1.123426000762122,0.5948585822502434,-0.37418168502153404,0.3012100164103108,1.4170745666020543,-0.9321139601174058,-1.5487759483812642,-1.5781408049652574,-1.4019516654612978,-1.313857095709318,0.06629116373836477,-1.2844922391253248,-0.7852896771974396,0.4773991559142703,-0.05116826259760824,-0.34481682843754075,-1.431316522045291,-1.4606813786292843,-0.5210059679415002,-0.16862768893358124,-0.8146545337814328,-0.6678302508614665,-0.4329113981895205,0.3599397295782973,-0.4329113981895205,0.06629116373836477,-0.46227625477351375,-0.5797356811094868,-1.0789382430373722,-1.4606813786292843,-0.5210059679415002,-1.167032812789352,0.4186694427462838,0.007561450570378263,-1.4900462352132775,-0.3154519718535475,0.06629116373836477,-0.139262832349588,-0.3154519718535475,-1.1083030996213654,-0.139262832349588,0.1543857334903445,-0.4329113981895205,-0.49164111135750704,-1.3725868088773046,-0.7852896771974396,0.56549372566625,0.06629116373836477,0.3012100164103108,-1.1083030996213654,0.5361288690822568,-0.28608711526955427,0.1543857334903445,0.3012100164103108,-0.726559964029453,-0.46227625477351375,-0.4329113981895205,-0.25672225868556103,-1.6075056615492507,-0.34481682843754075,0.007561450570378263

bayes-learning/seaborn-descr.py

@@ -0,0 +1,84 @@
+import pandas as pd
+import os
+import matplotlib
+import matplotlib.pyplot as plt
+# from sklearn.preprocessing import StandardScaler
+from sklearn.model_selection import train_test_split
+import numpy as np
+from scipy.stats import trim_mean, kurtosis
+from scipy.stats.mstats import mode, gmean, hmean
+
+
+def linebreak():
+    """prints a line break to split up functions"""
+    print('\n ============================================== \n')
+
+
+matplotlib.rcParams['backend'] = 'TkAgg'
+plt.style.use('seaborn-dark-palette')
+
+path = os.getcwd()
+data_file = str('/data/Social_Network_Ads.csv')
+
+df = pd.read_csv(path + data_file)
+# df = pd.DataFrame(df)
+
+df = df.sample(frac=1).reset_index(drop=True)
+
+print('{} rows. {} cols.'.format(df.shape[0], df.shape[1]))
+
+linebreak()
+print(df.iloc[0:10, :])
+
+linebreak()
+X = df[['Age', 'EstimatedSalary']]
+y = df['Purchased'].to_frame()
+
+print('X equals:')
+print(X.iloc[0:5])
+linebreak()
+print('y equals:')
+print(y[0:5])
+linebreak()
+
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33)
+
+description = df.describe().drop(columns=['User ID'])
+
+description_grouped = df.groupby(['Purchased'])
+
+description_grouped_split = description_grouped['Age', 'EstimatedSalary']\
+    .describe().unstack()
+
+description_grouped_mode = description_grouped['Age'].apply(mode, axis=None)
+
+df_quartile_slary = df.groupby('Purchased')['EstimatedSalary']\
+    .quantile([.1, .5, .9])
+df_quartile_age = df.groupby('Purchased')['Age'].quantile([.1, .5, .9])
+
+df_trimmed_mean = description_grouped['Age', 'EstimatedSalary'].\
+    aggregate(trim_mean, .1)
+
+df_summary = description_grouped['Age', 'EstimatedSalary']\
+    .aggregate([np.median, np.std, np.mean, gmean, hmean])
+
+df_var = description_grouped['Age', 'EstimatedSalary'].var()
+
+df_null = df.isna().sum()
+
+print(description)
+linebreak()
+print(description_grouped_split)
+linebreak()
+print(description_grouped_mode)
+linebreak()
+print(df_quartile_slary)
+print(df_quartile_age)
+linebreak()
+print(df_trimmed_mean)
+linebreak()
+print(df_summary)
+linebreak()
+print(df_var)
+linebreak()
+print(df_null)

bayes-learning/seaborn-graphing.py

@@ -0,0 +1,58 @@
+import pandas as pd
+import numpy as np
+import os
+import matplotlib
+import matplotlib.pyplot as plt
+from scipy.stats import trim_mean
+from scipy.stats.mstats import mode, gmean, hmean
+from sklearn.model_selection import train_test_split
+import seaborn as sns
+
+
+def linebreak():
+    """prints a line break to split up functions"""
+    print('\n ============================================== \n')
+
+
+matplotlib.rcParams['backend'] = 'TkAgg'
+# plt.style.use('seaborn-dark-palette')
+
+path = os.getcwd()
+data_file = str('/data/Social_Network_Ads.csv')
+
+df = pd.read_csv(path + data_file)
+
+df = df.sample(frac=1).reset_index(drop=True)
+
+print(df[0:5])
+
+X = df[['Age', 'EstimatedSalary']]
+y = df['Purchased']
+
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33)
+
+
+# ax1 = df.plot.scatter(x='Age', y='EstimatedSalary', c='DarkBlue')
+# ax2 = df.query('Age < 30').plot.scatter(x='Age', y='EstimatedSalary',
+# c='DarkBlue')
+
+
+# figure_1 = df.query('Age < 35').plot(kind='scatter', x='Age',
+# y='EstimatedSalary')
+
+df_purchased_sum = df['Purchased'].value_counts()
+
+# figure_2 = plt.plot(df_purchased_sum)
+
+# cp = sns.countplot(data=df, y='Purchased')
+
+# pal = dict(1="seagreen", 0="gray")
+
+fig, axs = plt.subplots(ncols=2)
+
+sns.countplot(data=df, x='Age', hue='Purchased', ax=axs[0])
+cp = sns.countplot(data=df, x='Purchased', ax=axs[1])
+
+plt.show()
+
+# print(df_purchased_sum)

bayes-learning/sites.txt

@@ -0,0 +1,60 @@
+https://medium.com/@urvashilluniya/why-data-normalization-is-necessary-for-machine-learning-models-681b65a05029
+
+visualise data
+https://towardsdatascience.com/the-art-of-effective-visualization-of-multi-dimensional-data-6c7202990c57
+
+https://www.marsja.se/pandas-python-descriptive-statistics/
+
+https://www.marsja.se/explorative-data-analysis-with-pandas-scipy-and-seaborn/
+
+
+
+deep learning https://towardsdatascience.com/detecting-malaria-with-deep-learning-9e45c1e34b60
+
+likelihood functions https://stats.stackexchange.com/questions/2641/what-is-the-difference-between-likelihood-and-probability
+
+
+plotting with df and matplotlib
+https://nbviewer.jupyter.org/urls/gist.github.com/fonnesbeck/5850463/raw/a29d9ffb863bfab09ff6c1fc853e1d5bf69fe3e4/3.+Plotting+and+Visualization.ipynb
+https://towardsdatascience.com/a-guide-to-pandas-and-matplotlib-for-data-exploration-56fad95f951c
+
+seaborne
+
+vis the dist
+https://seaborn.pydata.org/tutorial/distributions.html
+
+
+pdfs
+https://stats.stackexchange.com/questions/14483/intuitive-explanation-for-density-of-transformed-variable
+
+kernel
+https://mathisonian.github.io/kde/
+https://chemicalstatistician.wordpress.com/2013/06/09/exploratory-data-analysis-kernel-density-estimation-in-r-on-ozone-pollution-data-in-new-york-and-ozonopolis/
+https://www.quora.com/What-is-kernel-density-estimation
+choose bandwith so that it minimses the mean integrated square error so ban = min(MSIE)
+
+
+pandas plotting
+https://pandas.pydata.org/pandas-docs/stable/user_guide/visualization.html
+
+
+class
+https://jeffknupp.com/blog/2017/03/27/improve-your-python-python-classes-and-object-oriented-programming/
+https://realpython.com/python3-object-oriented-programming/
+
+errors
+https://doughellmann.com/blog/2009/06/19/python-exception-handling-techniques/
+
+public + private members
+https://www.tutorialsteacher.com/python/private-and-protected-access-modifiers-in-python
+
+properties
+https://www.programiz.com/python-programming/property
+
+
+generators
+https://pythontips.com/2013/09/29/the-python-yield-keyword-explained/
+https://www.programiz.com/python-programming/generator
+
+class methods with inheritence
+https://stackoverflow.com/questions/5738470/whats-an-example-use-case-for-a-python-classmethod

bayes-learning/snippets.txt

@@ -0,0 +1,6 @@
+from sklearn.cross_validation import train_test_split
+x_train, x_test, y_train, y_test = train_test_split(x, y , train_size = 0.7, random_state =  90)
+
+normalizing methods : https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/normalize-data
+                        https://en.wikipedia.org/wiki/Feature_scaling
+                        we apply the normalizing methods to the training data first, then seperately to the test data to compare!

bayes-learning/test.py

@@ -0,0 +1,21 @@
+import matplotlib.pyplot as plt
+import numpy as np
+import matplotlib.colors
+
+x = np.linspace(-3, 3)
+X, Y = np.meshgrid(x, x)
+Z = np.exp(-(X**2 + Y**2))
+fig, (ax, ax2) = plt.subplots(ncols=2)
+
+colors = ["red", "orange", "gold", "limegreen", "k",
+          "#550011", "purple", "seagreen"]
+
+ax.set_title("contour with color list")
+contour = ax.contourf(X, Y, Z, colors=colors)
+
+ax2.set_title("contour with colormap")
+cmap = matplotlib.colors.ListedColormap(colors)
+contour = ax2.contourf(X, Y, Z, cmap=cmap)
+fig.colorbar(contour)
+
+plt.show()