Related
X_train = {my training data features}
y_train = {my training data truth}
kf = KFold(n_splits=5, random_state=42, shuffle=True)
score = cross_val_score(SVC(), X_train, y_train, scoring = 'accuracy', cv = kf, n_jobs = -1)
gives this:
array([1. , 0.98717949, 1. , 1. , 0.98701299])
I run this code to get AUC:
tprs = []
aucs = []
mean_fpr = np.linspace(0, 1, 100)
plt.figure(figsize=(10,10))
i = 0
for train, test in kf.split(npX_train):
model = SVC(probability=True).fit(npX_train[train], npy_train[train])
probas_ = model.predict_proba(npX_train[test])
# Compute ROC curve and area the curve
fpr, tpr, thresholds = roc_curve(npy_train[test], probas_[:, 1])
tprs.append(interp(mean_fpr, fpr, tpr))
tprs[-1][0] = 0.0
roc_auc = auc(fpr, tpr)
aucs.append(roc_auc)
plt.plot(fpr, tpr, lw=1, alpha=0.3,
label='ROC fold %d (AUC = %0.2f)' % (i, roc_auc))
i += 1
plt.plot([0, 1], [0, 1], linestyle='--', lw=2, color='r',
label='Chance', alpha=.8)
mean_tpr = np.mean(tprs, axis=0)
mean_tpr[-1] = 1.0
mean_auc = auc(mean_fpr, mean_tpr)
std_auc = np.std(aucs)
plt.plot(mean_fpr, mean_tpr, color='b',
label=r'Mean ROC (AUC = %0.2f $\pm$ %0.2f)' % (mean_auc, std_auc),
lw=2, alpha=.8)
std_tpr = np.std(tprs, axis=0)
tprs_upper = np.minimum(mean_tpr + std_tpr, 1)
tprs_lower = np.maximum(mean_tpr - std_tpr, 0)
plt.fill_between(mean_fpr, tprs_lower, tprs_upper, color='grey', alpha=.2,
label=r'$\pm$ 1 std. dev.')
plt.xlim([-0.01, 1.01])
plt.ylim([-0.01, 1.01])
plt.xlabel('False Positive Rate',fontsize=18)
plt.ylabel('True Positive Rate',fontsize=18)
plt.title('Cross-Validation ROC of SVM',fontsize=18)
plt.legend(loc="lower right", prop={'size': 15})
plt.show()
which gives me this:
but if I get a confusion matrix for each iteration:
for train, test in kf.split(npX_train):
model = SVC(probability=True).fit(npX_train[train], npy_train[train])
# make confusion matrix plot for iteration
y_pred = model.predict(npX_train[test])
cm = confusion_matrix(npy_train[test], y_pred)
cm_display = ConfusionMatrixDisplay(cm).plot()
plot_confusion_matrix(model, npX_train[test], npy_train[test])
plt.plot()
The accuracy for label 1, which I care about does not look that great. Of the 22 true label 1, seems to get it right 20 times out of all runs.
My questions are:
Did I mess up that AUC plot or is that slight bend in the blue mean ROC line reflecting the inaccuracy of the model?
Is there a better way to evaluate accuracy for a biased input where I care about the accurate prediction of the more rare event?
For biased or imbalanced datasets use the metric F1 score. F1 score uses precision and recall.
Read for more detail on f1 score
https://medium.com/analytics-vidhya/accuracy-vs-f1-score-6258237beca2
Sklearn
https://scikit-learn.org/stable/modules/generated/sklearn.metrics.f1_score.html
I have some dataset which contains different paramteres and data.head() looks like this
Applied some preprocessing and performed Feature ranking -
dataset = pd.read_csv("ML.csv",header = 0)
#Get dataset breif
print(dataset.shape)
print(dataset.isnull().sum())
#print(dataset.head())
#Data Pre-processing
data = dataset.drop('organization_id',1)
data = data.drop('status',1)
data = data.drop('city',1)
#Find median for features having NaN
median_zip, median_role_id, median_specialty_id, median_latitude, median_longitude = data['zip'].median(),data['role_id'].median(),data['specialty_id'].median(),data['latitude'].median(),data['longitude'].median()
data['zip'].fillna(median_zip, inplace=True)
data['role_id'].fillna(median_role_id, inplace=True)
data['specialty_id'].fillna(median_specialty_id, inplace=True)
data['latitude'].fillna(median_latitude, inplace=True)
data['longitude'].fillna(median_longitude, inplace=True)
#Fill YearOFExp with 0
data['years_of_experience'].fillna(0, inplace=True)
target = dataset.location_id
#Perform Recursive Feature Extraction
svm = LinearSVC()
rfe = RFE(svm, 1)
rfe = rfe.fit(data, target) #IT give convergence Warning - Normally when an optimization algorithm does not converge, it is usually because the problem is not well-conditioned, perhaps due to a poor scaling of the decision variables.
names = list(data)
print("Features sorted by their score:")
print(sorted(zip(map(lambda x: round(x, 4), rfe.ranking_), names)))
Output
Features sorted by their score:
[(1, 'location_id'), (2, 'department_id'), (3, 'latitude'), (4, 'specialty_id'), (5, 'longitude'), (6, 'zip'), (7, 'shift_id'), (8, 'user_id'), (9, 'role_id'), (10, 'open_positions'), (11, 'years_of_experience')]
From this I understand that which parameters have more importance.
Is above processing correct to understand the feature important. How can I use above information for better model training?
When I to model training it gives very high accuracy. How come it gives so high accuracy?
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
dataset = pd.read_csv("prod_data_for_ML.csv",header = 0)
#Data Pre-processing
data = dataset.drop('location_id',1)
data = data.drop('status',1)
data = data.drop('city',1)
#Find median for features having NaN
median_zip, median_role_id, median_specialty_id, median_latitude, median_longitude = data['zip'].median(),data['role_id'].median(),data['specialty_id'].median(),data['latitude'].median(),data['longitude'].median()
data['zip'].fillna(median_zip, inplace=True)
data['role_id'].fillna(median_role_id, inplace=True)
data['specialty_id'].fillna(median_specialty_id, inplace=True)
data['latitude'].fillna(median_latitude, inplace=True)
data['longitude'].fillna(median_longitude, inplace=True)
#Fill YearOFExp with 0
data['years_of_experience'].fillna(0, inplace=True)
#Start training
labels = dataset.location_id
train1 = data
algo = LinearRegression()
x_train , x_test , y_train , y_test = train_test_split(train1 , labels , test_size = 0.20,random_state =1)
# x_train.to_csv("x_train.csv", sep=',', encoding='utf-8')
# x_test.to_csv("x_test.csv", sep=',', encoding='utf-8')
algo.fit(x_train,y_train)
algo.score(x_test,y_test)
output
0.981150074104111
from sklearn import ensemble
clf = ensemble.GradientBoostingRegressor(n_estimators = 400, max_depth = 5, min_samples_split = 2,
learning_rate = 0.1, loss = 'ls')
clf.fit(x_train, y_train)
clf.score(x_test,y_test)
Output -
0.99
Am I doing anything wrong? What ithe s correct way to build model for this sort of situati?n.
I know there is some way that I can get Precision, recall, f1 for each paramteres. Can anyone give me reference link to perform this?
Ive been trying to implement a basic multilayered LSTM regression network to find correlations between cryptocurrency prices.
After running into unusable training results, i've decided to play around with some sandbox code, to make sure i've got the idea right before trying again on my full dataset.
The problem is I can't get Keras to generalize my data.
ts = 3
in_dim = 1
data = [i*100 for i in range(10)]
# tried this, didn't accomplish anything
# data = [(d - np.mean(data))/np.std(data) for d in data]
x = data[:len(data) - 4]
y = data[3:len(data) - 1]
assert(len(x) == len(y))
x = [[_x] for _x in x]
y = [[_y] for _y in y]
x = [x[idx:idx + ts] for idx in range(0, len(x), ts)]
y = [y[idx:idx + ts] for idx in range(0, len(y), ts)]
x = np.asarray(x)
y = np.asarray(y)
x looks like this:
[[[ 0]
[100]
[200]]
[[300]
[400]
[500]]]
and y:
[[[300]
[400]
[500]]
[[600]
[700]
[800]]]
and this works well when I predict using a very similar dataset, but doesn't generalize when I try a similar sequence with scaled values
model = Sequential()
model.add(BatchNormalization(
axis = 1,
input_shape = (ts, in_dim)))
model.add(LSTM(
100,
input_shape = (ts, in_dim),
return_sequences = True))
model.add(TimeDistributed(Dense(in_dim)))
model.add(Activation('linear'))
model.compile(loss = 'mse', optimizer = 'rmsprop')
model.fit(x, y, epochs = 2000, verbose = 0)
p = np.asarray([[[10],[20],[30]]])
prediction = model.predict(p)
print(prediction)
prints
[[[ 165.78544617]
[ 209.34489441]
[ 216.02174377]]]
I want
[[[ 40.0000]
[ 50.0000]
[ 60.0000]]]
how can I format this so that when i plug in a sequence with values that are of a completely different scale, the network will still output its predicted value? I've tried normalizing my training data, but the results are still entirely unusable.
What have I done wrong here?
How about transform your input data before sending into your LSTM, use something like sklearn.preprocessing.StandardScaler? after prediction you can call scaler.inverse_transform(prediction)
I am very new to TensorFlow and I am in parallel learning traditional machine learning techniques. Previously, I was able to successfully implement linear regression modelling in matlab and in Python using scikit.
When I tried to reproduce it using Tensorflow with the same dataset, I am getting invalid outputs. Could someone advise me on where I am making the mistake or what I am missing!
Infact, I am using the code from tensor flow introductory tutorial and I just changed the x_train and y_train to a different data set.
# Loading the ML coursera course ex1 (Wk 2) data to try it out
'''
path = r'C:\Users\Prasanth\Dropbox\Python Folder\ML in Python\data\ex1data1.txt'
fh = open(path,'r')
l1 = []
l2 = []
for line in fh:
temp = (line.strip().split(','))
l1.append(float(temp[0]))
l2.append(float(temp[1]))
'''
l1 = [6.1101, 5.5277, 8.5186, 7.0032, 5.8598, 8.3829, 7.4764, 8.5781, 6.4862, 5.0546, 5.7107, 14.164, 5.734, 8.4084, 5.6407, 5.3794, 6.3654, 5.1301, 6.4296, 7.0708, 6.1891, 20.27, 5.4901, 6.3261, 5.5649, 18.945, 12.828, 10.957, 13.176, 22.203, 5.2524, 6.5894, 9.2482, 5.8918, 8.2111, 7.9334, 8.0959, 5.6063, 12.836, 6.3534, 5.4069, 6.8825, 11.708, 5.7737, 7.8247, 7.0931, 5.0702, 5.8014, 11.7, 5.5416, 7.5402, 5.3077, 7.4239, 7.6031, 6.3328, 6.3589, 6.2742, 5.6397, 9.3102, 9.4536, 8.8254, 5.1793, 21.279, 14.908, 18.959, 7.2182, 8.2951, 10.236, 5.4994, 20.341, 10.136, 7.3345, 6.0062, 7.2259, 5.0269, 6.5479, 7.5386, 5.0365, 10.274, 5.1077, 5.7292, 5.1884, 6.3557, 9.7687, 6.5159, 8.5172, 9.1802, 6.002, 5.5204, 5.0594, 5.7077, 7.6366, 5.8707, 5.3054, 8.2934, 13.394, 5.4369]
l2 = [17.592, 9.1302, 13.662, 11.854, 6.8233, 11.886, 4.3483, 12.0, 6.5987, 3.8166, 3.2522, 15.505, 3.1551, 7.2258, 0.71618, 3.5129, 5.3048, 0.56077, 3.6518, 5.3893, 3.1386, 21.767, 4.263, 5.1875, 3.0825, 22.638, 13.501, 7.0467, 14.692, 24.147, -1.22, 5.9966, 12.134, 1.8495, 6.5426, 4.5623, 4.1164, 3.3928, 10.117, 5.4974, 0.55657, 3.9115, 5.3854, 2.4406, 6.7318, 1.0463, 5.1337, 1.844, 8.0043, 1.0179, 6.7504, 1.8396, 4.2885, 4.9981, 1.4233, -1.4211, 2.4756, 4.6042, 3.9624, 5.4141, 5.1694, -0.74279, 17.929, 12.054, 17.054, 4.8852, 5.7442, 7.7754, 1.0173, 20.992, 6.6799, 4.0259, 1.2784, 3.3411, -2.6807, 0.29678, 3.8845, 5.7014, 6.7526, 2.0576, 0.47953, 0.20421, 0.67861, 7.5435, 5.3436, 4.2415, 6.7981, 0.92695, 0.152, 2.8214, 1.8451, 4.2959, 7.2029, 1.9869, 0.14454, 9.0551, 0.61705]
print ('List length and data type', len(l1), type(l1))
#------------------#
import tensorflow as tf
# Model parameters
W = tf.Variable([0], dtype=tf.float64)
b = tf.Variable([0], dtype=tf.float64)
# Model input and output
x = tf.placeholder(tf.float64)
linear_model = W * x + b
y = tf.placeholder(tf.float64)
# loss or cost function
loss = tf.reduce_sum(tf.square(linear_model - y)) # sum of the squares
# optimizer (gradient descent) with learning rate = 0.01
optimizer = tf.train.GradientDescentOptimizer(0.01)
train = optimizer.minimize(loss)
# training data (labelled input & output swt)
# Using coursera data instead of sample data
#x_train = [1.0, 2, 3, 4]
#y_train = [0, -1, -2, -3]
x_train = l1
y_train = l2
# training loop (1000 iterations)
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init) # reset values to wrong
for i in range(1000):
sess.run(train, {x: x_train, y: y_train})
# evaluate training accuracy
curr_W, curr_b, curr_loss = sess.run([W, b, loss], {x: x_train, y: y_train})
print("W: %s b: %s loss: %s"%(curr_W, curr_b, curr_loss))
Output
List length and data type: 97 <class 'list'>
W: [ nan] b: [ nan] loss: nan
One major problem with your estimator is the loss function. Since you use tf.reduce_sum, the loss grows with the number of samples, which you have to compensate by using a smaller learning rate. A better solution would be to use mean square error loss
loss = tf.reduce_mean(tf.square(linear_model - y))
I am using sklearn for multi-classification task. I need to split alldata into train_set and test_set. I want to take randomly the same sample number from each class.
Actually, I amusing this function
X_train, X_test, y_train, y_test = cross_validation.train_test_split(Data, Target, test_size=0.3, random_state=0)
but it gives unbalanced dataset! Any suggestion.
Although Christian's suggestion is correct, technically train_test_split should give you stratified results by using the stratify param.
So you could do:
X_train, X_test, y_train, y_test = cross_validation.train_test_split(Data, Target, test_size=0.3, random_state=0, stratify=Target)
The trick here is that it starts from version 0.17 in sklearn.
From the documentation about the parameter stratify:
stratify : array-like or None (default is None)
If not None, data is split in a stratified fashion, using this as the labels array.
New in version 0.17: stratify splitting
You can use StratifiedShuffleSplit to create datasets featuring the same percentage of classes as the original one:
import numpy as np
from sklearn.model_selection import StratifiedShuffleSplit
X = np.array([[1, 3], [3, 7], [2, 4], [4, 8]])
y = np.array([0, 1, 0, 1])
stratSplit = StratifiedShuffleSplit(y, n_iter=1, test_size=0.5, random_state=42)
for train_idx, test_idx in stratSplit:
X_train=X[train_idx]
y_train=y[train_idx]
print(X_train)
# [[3 7]
# [2 4]]
print(y_train)
# [1 0]
If the classes are not balanced but you want the split to be balanced, then stratifying isn't going to help. There doesn't seem to be a method for doing balanced sampling in sklearn but it's kind of easy using basic numpy, for example a function like this might help you:
def split_balanced(data, target, test_size=0.2):
classes = np.unique(target)
# can give test_size as fraction of input data size of number of samples
if test_size<1:
n_test = np.round(len(target)*test_size)
else:
n_test = test_size
n_train = max(0,len(target)-n_test)
n_train_per_class = max(1,int(np.floor(n_train/len(classes))))
n_test_per_class = max(1,int(np.floor(n_test/len(classes))))
ixs = []
for cl in classes:
if (n_train_per_class+n_test_per_class) > np.sum(target==cl):
# if data has too few samples for this class, do upsampling
# split the data to training and testing before sampling so data points won't be
# shared among training and test data
splitix = int(np.ceil(n_train_per_class/(n_train_per_class+n_test_per_class)*np.sum(target==cl)))
ixs.append(np.r_[np.random.choice(np.nonzero(target==cl)[0][:splitix], n_train_per_class),
np.random.choice(np.nonzero(target==cl)[0][splitix:], n_test_per_class)])
else:
ixs.append(np.random.choice(np.nonzero(target==cl)[0], n_train_per_class+n_test_per_class,
replace=False))
# take same num of samples from all classes
ix_train = np.concatenate([x[:n_train_per_class] for x in ixs])
ix_test = np.concatenate([x[n_train_per_class:(n_train_per_class+n_test_per_class)] for x in ixs])
X_train = data[ix_train,:]
X_test = data[ix_test,:]
y_train = target[ix_train]
y_test = target[ix_test]
return X_train, X_test, y_train, y_test
Note that if you use this and sample more points per class than in the input data, then those will be upsampled (sample with replacement). As a result, some data points will appear multiple times and this may have an effect on the accuracy measures etc. And if some class has only one data point, there will be an error. You can easily check the numbers of points per class for example with np.unique(target, return_counts=True)
Another approach is to over- or under- sample from your stratified test/train split. The imbalanced-learn library is quite handy for this, specially useful if you are doing online learning & want to guarantee balanced train data within your pipelines.
from imblearn.pipeline import Pipeline as ImbalancePipeline
model = ImbalancePipeline(steps=[
('data_balancer', RandomOverSampler()),
('classifier', SVC()),
])
This is my implementation that I use to get train/test data indexes
def get_safe_balanced_split(target, trainSize=0.8, getTestIndexes=True, shuffle=False, seed=None):
classes, counts = np.unique(target, return_counts=True)
nPerClass = float(len(target))*float(trainSize)/float(len(classes))
if nPerClass > np.min(counts):
print("Insufficient data to produce a balanced training data split.")
print("Classes found %s"%classes)
print("Classes count %s"%counts)
ts = float(trainSize*np.min(counts)*len(classes)) / float(len(target))
print("trainSize is reset from %s to %s"%(trainSize, ts))
trainSize = ts
nPerClass = float(len(target))*float(trainSize)/float(len(classes))
# get number of classes
nPerClass = int(nPerClass)
print("Data splitting on %i classes and returning %i per class"%(len(classes),nPerClass ))
# get indexes
trainIndexes = []
for c in classes:
if seed is not None:
np.random.seed(seed)
cIdxs = np.where(target==c)[0]
cIdxs = np.random.choice(cIdxs, nPerClass, replace=False)
trainIndexes.extend(cIdxs)
# get test indexes
testIndexes = None
if getTestIndexes:
testIndexes = list(set(range(len(target))) - set(trainIndexes))
# shuffle
if shuffle:
trainIndexes = random.shuffle(trainIndexes)
if testIndexes is not None:
testIndexes = random.shuffle(testIndexes)
# return indexes
return trainIndexes, testIndexes
This is the function I am using. You can adapt it and optimize it.
# Returns a Test dataset that contains an equal amounts of each class
# y should contain only two classes 0 and 1
def TrainSplitEqualBinary(X, y, samples_n): #samples_n per class
indicesClass1 = []
indicesClass2 = []
for i in range(0, len(y)):
if y[i] == 0 and len(indicesClass1) < samples_n:
indicesClass1.append(i)
elif y[i] == 1 and len(indicesClass2) < samples_n:
indicesClass2.append(i)
if len(indicesClass1) == samples_n and len(indicesClass2) == samples_n:
break
X_test_class1 = X[indicesClass1]
X_test_class2 = X[indicesClass2]
X_test = np.concatenate((X_test_class1,X_test_class2), axis=0)
#remove x_test from X
X_train = np.delete(X, indicesClass1 + indicesClass2, axis=0)
Y_test_class1 = y[indicesClass1]
Y_test_class2 = y[indicesClass2]
y_test = np.concatenate((Y_test_class1,Y_test_class2), axis=0)
#remove y_test from y
y_train = np.delete(y, indicesClass1 + indicesClass2, axis=0)
if (X_test.shape[0] != 2 * samples_n or y_test.shape[0] != 2 * samples_n):
raise Exception("Problem with split 1!")
if (X_train.shape[0] + X_test.shape[0] != X.shape[0] or y_train.shape[0] + y_test.shape[0] != y.shape[0]):
raise Exception("Problem with split 2!")
return X_train, X_test, y_train, y_test