added project 3 files

project 3/.gitignore

+files
+files/
+output/
+__pycache__

project 3/augment.py

@@ -64,7 +64,6 @@ def augment():
     
     
     # data augmentation
-    # TODO : augment
     X_train_scaled, X_test_scaled = scale(X_train_mod, X_test_mod)
     X_train_ones = X_train_mod + np.ones_like(X_train_mod)
     X_test_ones  = X_test_mod + np.ones_like(X_test_mod)

project 3/impute.py

+from sklearn.impute import SimpleImputer
+import numpy as np
+
+def impute(X, strategy = 'mean'):
+    imp_mean = SimpleImputer(missing_values=np.nan, strategy='mean')
+    imp_mean.fit(X)
+    X_mod = imp_mean.transform(X)
+    return X_mod
\ No newline at end of file

project 3/lstm.py

+# -*- coding: utf-8 -*-
+"""
+Created on Mon Nov 25 19:22:20 2019
+
+@author: made_
+"""
+import numpy as np
+import pandas as pd
+import keras
+from sklearn.preprocessing import StandardScaler
+from keras.models import Sequential
+from keras.layers import Dropout, LSTM, Dense
+
+# libraries when working in Colaboratory
+#from google.colab import files
+
+
+# get data
+X_train = pd.read_csv('files/X_train_aug.csv').values[:,1:]
+y_train = pd.read_csv('files/y_train.csv').values[:,1 ]
+X_test  = pd.read_csv('files/X_test_aug.csv').values[:,1:]
+
+
+z,s = np.shape(X_train)
+        
+scaler = StandardScaler()
+scaler.fit(X_train)
+X_transformed = scaler.transform(X_train)
+Xtest_transformed = scaler.transform(X_test)
+
+# define the model architecture
+lahead = s
+ann = Sequential()
+ann.add(LSTM(1024, input_shape = (lahead,1), activation = 'relu',
+             return_sequences = True))
+ann.add(Dropout(0.2))
+
+ann.add(LSTM(512, activation = 'relu'))
+ann.add(Dropout(0.25))
+
+#ann.add(LSTM(512, activation = 'relu'))
+#ann.add(Dropout(0.25))
+#
+#ann.add(LSTM(256, activation = 'relu'))
+#ann.add(Dropout(0.25))
+
+ann.add(Dense(128, activation = 'relu'))
+ann.add(Dropout(0.25))
+
+ann.add(Dense(4, activation='softmax'))
+
+opt = keras.optimizers.Adam(lr = 1e-3, decay = 1e-5)
+
+ann.compile(loss = 'sparse_categorical_crossentropy',
+            optimizer = opt,
+            metrics = ['accuracy'])
+# reshape to fulfill LSTM shape requirements
+reshape_1 = lambda x: x.reshape((x.shape[0], x.shape[1], 1))  # reshape x trainset
+reshape_2 = lambda y: y.reshape((y.shape[0], 1))              # reshape y
+X_reshaped = reshape_1(X_train)
+Xtest_reshaped = reshape_1(Xtest_transformed)
+y_reshaped = reshape_2(y_train)
+
+# fit and predict (later add class weights and also optimize them)
+ann.fit(X_reshaped, y_reshaped, epochs = 1000, batch_size = 500)
+pred_ann = ann.predict_classes(Xtest_reshaped)
+print(pred_ann)
\ No newline at end of file

project 3/modify.py

+# -*- coding: utf-8 -*-
+"""
+Created on Mon Nov 18 15:53:27 2019
+
+@author: made_
+"""
+
+import numpy as np
+import pandas as pd
+from sklearn.impute import SimpleImputer
+from sklearn.ensemble import IsolationForest
+from scale import scale
+from outliers import outliers
+from impute import impute
+
+
+def modify():
+    # import data
+    X_train = pd.read_csv('files/X_train.csv').values[:,1:]
+    y_train = pd.read_csv('files/y_train.csv').values[:,1 ]
+    X_test  = pd.read_csv('files/X_test.csv').values[:,1:]
+    
+    z,s = np.shape(X_train)
+    z_,s_ = np.shape(X_test)
+    
+    # check if balanced
+    print('Size of X:', np.shape(X_train))
+    print('Classes in y:',np.unique(y_train))
+    iter_i = 0
+    print('Class Balance')
+    while iter_i != len(np.unique(y_train)):
+        print('    Data for Class %s: ' %iter_i, len(y_train[np.where(y_train==iter_i)]))
+        iter_i += 1
+    
+    
+    # check for presence of nans
+    isnan_train = np.zeros(s, dtype=int)
+    isnan_test  = np.zeros(s, dtype=int)
+    for i in range(s):
+        isnan_train[i] = np.sum(np.isnan(X_train[:,i]))
+        isnan_test[i] = np.sum(np.isnan(X_test[:,i]))
+    
+    # modify to keep only those features with less than #n nans in X_train
+    X_train_mod = X_train[:,isnan_train < 300]
+    X_test_mod  = X_test[:,isnan_train < 300]  # apply same reduction to testset as in trainset
+    
+    
+    # use simple procedure to replace nans
+    X_train_mod = impute(X_train_mod)
+    X_test_mod  = impute(X_test_mod)
+    
+    
+    # check for outliers - causes problems when writing y_pred to csv
+#    train_inliers = outliers(X_train_mod)
+#    test_inliers = outliers(X_test_mod)
+#    X_train_mod = X_train_mod[train_inliers, :]
+#    X_test_mod = X_test_mod[test_inliers, :]
+#    y_train = y_train[train_inliers]
+    
+    
+    # scale data after the previous procedure
+#    X_train_mod, X_test_mod = scale(X_train_mod, X_test_mod)
+    
+    # saving of modified data for quicker usage
+    pd.DataFrame(X_train_mod).to_csv('files/X_train_mod.csv')
+    pd.DataFrame(X_test_mod).to_csv('files/X_test_mod.csv')
+#    pd.DataFrame(y_train).to_csv('files/y_train_mod.csv')
+    
\ No newline at end of file

project 3/outliers.py

+import numpy as np
+from sklearn.ensemble import IsolationForest
+
+# remove outliers
+def outliers(X, n_trees = 100, outlier_proportion = 0.15):
+    outliers = IsolationForest(n_estimators=n_trees,
+                               behaviour='new',
+                               contamination=outlier_proportion)
+    outliers.fit(X)
+    inlier_indices = np.nonzero(outliers.predict(X) > 0)[0]
+    
+    return inlier_indices
\ No newline at end of file

project 3/outputs/OneVsOneClassifier.RandomForestClassifier.csv

+id,y
+0,0
+1,0
+2,0
+3,0
+4,0
+5,0
+6,0
+7,0
+8,0
+9,0
+10,0
+11,0
+12,0
+13,0
+14,0
+15,0
+16,0
+17,0
+18,0
+19,0
+20,0
+21,0
+22,0
+23,0
+24,0
+25,0
+26,0
+27,0
+28,0
+29,0
+30,0
+31,0
+32,0
+33,0
+34,0
+35,0
+36,0
+37,0
+38,0
+39,0
+40,0
+41,0
+42,0
+43,0
+44,0
+45,0
+46,0
+47,2
+48,0
+49,0
+50,0
+51,0
+52,0
+53,0
+54,0
+55,0
+56,0
+57,0
+58,0
+59,0
+60,0
+61,0
+62,0
+63,0
+64,0
+65,0
+66,0
+67,0
+68,0
+69,0
+70,0
+71,0
+72,0
+73,0
+74,0
+75,2
+76,0
+77,0
+78,0
+79,0
+80,0
+81,0
+82,0
+83,0
+84,0
+85,0
+86,2
+87,0
+88,0
+89,0
+90,2
+91,0
+92,0
+93,0
+94,0
+95,0
+96,0
+97,0
+98,0
+99,0
+100,0
+101,0
+102,0
+103,0
+104,0
+105,0
+106,0
+107,0
+108,0
+109,0
+110,0
+111,0
+112,0
+113,0
+114,0
+115,0
+116,0
+117,0
+118,0
+119,0
+120,0
+121,0
+122,0
+123,0
+124,0
+125,0
+126,0
+127,0
+128,0
+129,2
+130,0
+131,0
+132,0
+133,0
+134,0
+135,0
+136,0
+137,0
+138,0
+139,0
+140,0
+141,0
+142,0
+143,0
+144,0
+145,0
+146,0
+147,0
+148,0
+149,0
+150,0
+151,0
+152,0
+153,0
+154,0
+155,0
+156,0
+157,0
+158,0
+159,0
+160,0
+161,0
+162,0
+163,0
+164,0
+165,0
+166,0
+167,0
+168,0
+169,0
+170,0
+171,0
+172,0
+173,0
+174,2
+175,0
+176,0
+177,0
+178,0
+179,0
+180,0
+181,0
+182,0
+183,0
+184,0
+185,0
+186,0
+187,0
+188,0
+189,0
+190,0
+191,2
+192,0
+193,0
+194,0
+195,0
+196,0
+197,0
+198,0
+199,0
+200,0
+201,0
+202,0
+203,0
+204,0
+205,0
+206,0
+207,0
+208,0
+209,0
+210,0
+211,0
+212,0
+213,0
+214,0
+215,0
+216,0
+217,0
+218,0
+219,0
+220,0
+221,0
+222,0
+223,0
+224,0
+225,0
+226,0
+227,0
+228,0
+229,0
+230,0
+231,0
+232,0
+233,0
+234,0
+235,0
+236,0
+237,0
+238,0
+239,0
+240,0
+241,0
+242,0
+243,0
+244,0
+245,0
+246,0
+247,0
+248,0
+249,0
+250,0
+251,0
+252,0
+253,0
+254,0
+255,0
+256,0
+257,0
+258,0
+259,0
+260,0
+261,0
+262,0
+263,0
+264,0
+265,0
+266,0
+267,0
+268,0
+269,0
+270,0
+271,0
+272,0
+273,0
+274,0
+275,0
+276,0
+277,0
+278,0
+279,0
+280,0
+281,0
+282,0
+283,0
+284,0
+285,0
+286,0
+287,0
+288,0
+289,0
+290,0
+291,0
+292,0
+293,0
+294,0
+295,0
+296,0
+297,0
+298,0
+299,0
+300,0
+301,0
+302,0
+303,0
+304,0
+305,0
+306,0
+307,0
+308,0
+309,0
+310,0
+311,0
+312,0
+313,0
+314,0
+315,0
+316,0
+317,0
+318,0
+319,0
+320,0
+321,0
+322,0
+323,0
+324,0
+325,0
+326,0
+327,0
+328,0
+329,0
+330,0
+331,0
+332,0
+333,0
+334,0
+335,0
+336,0
+337,0
+338,0
+339,0
+340,0
+341,0
+342,0
+343,0
+344,0
+345,0
+346,0
+347,0
+348,0
+349,0
+350,0
+351,0
+352,0
+353,0
+354,0
+355,0
+356,0
+357,0
+358,0
+359,0
+360,0
+361,0
+362,0
+363,0
+364,0
+365,0
+366,0
+367,0
+368,0
+369,0
+370,0
+371,0
+372,0
+373,0
+374,0
+375,0
+376,0
+377,0
+378,0
+379,0
+380,0
+381,0
+382,0
+383,2
+384,0
+385,0
+386,0
+387,0
+388,0
+389,0
+390,0
+391,0
+392,0
+393,0
+394,0
+395,0
+396,0
+397,0
+398,0
+399,0
+400,0
+401,0
+402,0
+403,0
+404,0
+405,0
+406,0
+407,0
+408,0
+409,0
+410,0
+411,0
+412,0
+413,0
+414,0
+415,0
+416,0
+417,0
+418,0
+419,0
+420,0
+421,0
+422,0
+423,0
+424,0
+425,0
+426,0
+427,0
+428,0
+429,0
+430,0
+431,0
+432,0
+433,0
+434,0
+435,0
+436,0
+437,0
+438,0
+439,0
+440,0
+441,0
+442,0
+443,0
+444,0
+445,0
+446,0
+447,0
+448,0