I'm trying to figure out how to implement Principal Coordinate Analysis with various distance metrics. I stumbled across both skbio and sklearn with implementations. I don't understand why sklearn's implementation is different everytime while skbio is the same? Is there a degree of randomness to Multidimensional Scaling and in particular Principal Coordinate Analysis? I see that all of the clusters are very similar but why are they different? Am I implementing this correctly?
Running Principal Coordinate Analysis using Scikit-bio (i.e. Skbio) always gives the same results:
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.datasets import load_iris
from sklearn.preprocessing import StandardScaler
from sklearn import decomposition
import seaborn as sns; sns.set_style("whitegrid", {'axes.grid' : False})
import skbio
from scipy.spatial import distance
%matplotlib inline
np.random.seed(0)
# Iris dataset
DF_data = pd.DataFrame(load_iris().data,
index = ["iris_%d" % i for i in range(load_iris().data.shape[0])],
columns = load_iris().feature_names)
n,m = DF_data.shape
# print(n,m)
# 150 4
Se_targets = pd.Series(load_iris().target,
index = ["iris_%d" % i for i in range(load_iris().data.shape[0])],
name = "Species")
# Scaling mean = 0, var = 1
DF_standard = pd.DataFrame(StandardScaler().fit_transform(DF_data),
index = DF_data.index,
columns = DF_data.columns)
# Distance Matrix
Ar_dist = distance.squareform(distance.pdist(DF_data, metric="braycurtis")) # (n x n) distance measure
DM_dist = skbio.stats.distance.DistanceMatrix(Ar_dist, ids=DF_standard.index)
PCoA = skbio.stats.ordination.pcoa(DM_dist)
Now with sklearn's Multidimensional Scaling:
from sklearn.manifold import MDS
fig, ax=plt.subplots(ncols=5, figsize=(12,3))
for rs in range(5):
M = MDS(n_components=2, metric=True, random_state=rs, dissimilarity='precomputed')
A = M.fit(Ar_dist).embedding_
ax[rs].scatter(A[:,0],A[:,1], c=[{0:"b", 1:"g", 2:"r"}[t] for t in Se_targets])
scikit-bio's PCoA (skbio.stats.ordination.pcoa) and scikit-learn's MDS (sklearn.manifold.MDS) use entirely different algorithms to transform the data. scikit-bio directly solves a symmetric eigenvalue problem and scikit-learn uses an iterative minimization procedure [1].
scikit-bio's PCoA is deterministic, though it is possible to receive different (arbitrary) rotations of the transformed coordinates depending on the system it is executed on [2]. scikit-learn's MDS is stochastic by default unless a fixed random_state is used. random_state appears to be used to initialize the iterative minimization procedure (the scikit-learn docs say that random_state is used to "initialize the centers" [3] though I don't know exactly what that means). Each random_state may produce slightly different embeddings with arbitrary rotation [4].
References: [1], [2], [3], [4]
MDS is a probabalistic algorithm, there is a parameter random_state that you can use to fix the random seed, you can pass this if you want to get the same results each time. PCA on the other hand is a deterministic algorithm, if you use sklearn.decomposition.PCA, you should get the same results each time.
Related
My LightGBM regressor model returns negative values.
For XGBoost there is objective='count:poisson' hyperparameter in order to prevent returning negative predicitons.
Is there any chance to do this ?
Github issue => https://github.com/microsoft/LightGBM/issues/5629
LightGBM also supports poisson regression. For example, consider the following Python code.
import lightgbm as lgb
import numpy as np
from matplotlib import pyplot
# random Poisson-distributed target and one informative feature
y = np.random.poisson(lam=15.0, size=1_000)
X = y + np.random.normal(loc=10.0, scale=2.0, size=(y.shape[0], ))
X = X.reshape(-1, 1)
# fit a Poisson regression model
reg = lgb.LGBMRegressor(
objective="poisson",
n_estimators=150,
min_data=1
)
reg.fit(X, y)
# get predictions
preds = reg.predict(X)
print("summary of predicted values")
print(f" * min: {round(np.min(preds), 3)}")
print(f" * max: {round(np.max(preds), 3)}")
# compare predicted distribution to the empirical one
bins = np.linspace(0, 30, 50)
pyplot.hist(y, bins, alpha=0.5, label='actual')
pyplot.hist(preds, bins, alpha=0.5, label='predicted')
pyplot.legend(loc='upper right')
pyplot.show()
This example uses Python 3.10 and lightgbm==3.3.3.
However... I don't recommend using Poisson regression just to achieve "no negative predictions". The Poisson loss function is intended to be used for cases where you believe your target is Poisson-distributed, e.g. it looks like counts of events observed over some regular interval like time or space.
Other options you might consider to try to achieve the behavior "never predict a negative number from LightGBM regression":
write a custom objective function in one of the interfaces that support it, like the R or Python package
post-process LightGBM's predictions, recoding negative values to 0
pre-process the target variable such that there are no negative values (e.g. dropping such observations, re-scaling, taking the absolute value)
LightGBM also facilitates an objective parameter which can be set to 'poisson'. Follow this link for more information.
An example for LGBMRegressor (scikit-learn API):
from lightgbm import LGBMRegressor
regressor = LGBMRegressor(objective='poisson')
I am working on a prediction problem. In my training set, I have around 8,700 samples and around 1,000 features. I used different models but still, it is highly biased. So, I decided to add new features to the model. I added some lags to the features and then used the polynomial tools in sklearn to generate polynomial features (degree=2).
from sklearn.preprocessing import PolynomialFeatures
poly = PolynomialFeatures(2)
X_poly = poly.fit_transform(X)
X = pd.DataFrame(X_poly, columns=poly.get_feature_names_out(), index=X.index)
Now, I have around 490,000 features. Next, when I want to do the feature scaling,
from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X)
I face an error in jupyternotebook saying "dead kernel" and I cannot go further.
What should I do? Any suggestion?
You need to do a batch processing with partial fit and then transform (also needs a loop):
scaler = StandardScaler()
n = X.shape[0] # rows
batch_size = 1000
i = 0
while i < n:
partial_size = min(batch_size, n - i)
partial_x = X[i:i + partial_size]
scaler.partial_fit(partial_x)
i += partial_size
I have a multi-class confusion matrix as below and would like to draw its associated ROC curve for one of its classes (e.g. class 1). I know the "one-VS-all others" theory should be used in this case, but I want to know how exactly we need to change the threshold to obtain different pairs of TP and corresponding FP rates.enter image description here
SkLearn has a handy implementation which calculates the tpr and fpr and another function which generates the auc for you. You can just apply this to your data by treating each class on its own (all other data being negative) by looping through each class. The code below was inspired by the scikit-learn page on this topic itself.
import numpy as np
from sklearn.metrics import roc_auc_score
from sklearn.metrics import roc_curve, auc
import matplotlib.pyplot as plt
#generating synthetic data
N_classes = 3
N_per_class=100
labels = np.concatenate([[i]*N_per_class for i in range(N_classes)])
preds = np.stack([np.random.uniform(0,1,N_per_class*N_classes) for _ in range(N_classes)]).T
preds /= preds.sum(1,keepdims=True) #approximate softmax
tpr,fpr,roc_auc = ([[]]*N_classes for _ in range(3))
f,ax = plt.subplots()
#generate ROC data
for i in range(N_classes):
fpr[i], tpr[i], _ = roc_curve(labels==i, preds[:, i])
roc_auc[i] = auc(fpr[i], tpr[i])
ax.plot(fpr[i],tpr[i])
plt.legend(['Class {:d}'.format(d) for d in range(N_classes)])
plt.xlabel('FPR')
plt.ylabel('TPR')
Just a brief idea of my situation:
I have 4 columns of input: id, text, category, label.
I used TFIDFVectorizer on the text which gives me a list of instances with word tokens of TFIDF score.
Now I'd like to include the category (no need to pass TFIDF) as another feature in the data outputed by the vectorizer.
Also note that prior to the vectorization, the data have passed train_test_split.
How could I achieve this?
Initial code:
#initialization
import pandas as pd
path = 'data\data.csv'
rappler= pd.read_csv(path)
X = rappler.text
y = rappler.label
#rappler.category - contains category for each instance
#split train test data
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=1)
#feature extraction
from sklearn.feature_extraction.text import CountVectorizer
vect = CountVectorizer()
X_train_dtm = vect.fit_transform(X_train)
#after or even prior to perform fit_transform, how can I properly add category as a feature?
X_test_dtm = vect.transform(X_test)
#actual classfication
from sklearn.naive_bayes import MultinomialNB
nb = MultinomialNB()
nb.fit(X_train_dtm, y_train)
y_pred_class = nb.predict(X_test_dtm)
#display result
from sklearn import metrics
print(metrics.accuracy_score(y_test,y_pred_class))
I would suggest doing your train test split after feature extraction.
Once you have the TF-IDF feature lists just add the other feature for each sample.
You will have to encode the category feature, a good choice would be sklearn's LabelEncoder. Then you should have two sets of numpy arrays that can be joined.
Here is a toy example:
X_tfidf = np.array([[0.1, 0.4, 0.2], [0.5, 0.4, 0.6]])
X_category = np.array([[1], [2]])
X = np.concatenate((X_tfidf, X_category), axis=1)
At this point you would continue as you were, starting with the train test split.
You should use FeatureUnions - as explained in the documentation
FeatureUnions combines several transformer objects into a new
transformer that combines their output. A FeatureUnion takes a list of
transformer objects. During fitting, each of these is fit to the data
independently. For transforming data, the transformers are applied in
parallel, and the sample vectors they output are concatenated
end-to-end into larger vectors.
Another good example on how to use FeatureUnions can be found here: http://scikit-learn.org/stable/auto_examples/hetero_feature_union.html
Just concatenating different matrices like #AlexG suggests is probably an easier option but FeatureUnions is the scikit-learn way to do these things.
I built a random forest and I want to find the out of bag score.But my out of bag score is coming out to be 1.0,but it should be less than 1.My sample size consists of 20000 elements.Here is the python code.Please tell the changes to be done.Here X is a numpy array of datasets and Z contains true labels.
import csv
import numpy as np
from sklearn import preprocessing
from sklearn import cross_validation
from sklearn.ensemble import RandomForestClassifier
with open('C:\Users\Harsh Bhandari\Desktop\letter.csv') as f:
reader = csv.reader(f, delimiter='\t')
data = [(col1, int(col2), int(col3), int(col4),int(col5),int(col6),int(col7),int(col8),int(col9),int(col10),int(col11),int(col12),int(col13),int(col14),int(col15),int(col16),int(col17))
for col1,col2,col3,col4,col5,col6,col7,col8,col9,col10,col11,col12,col13,col14,col15,col16,col17 in reader]
X=[]
Y=[]
i=0
while i<20000:
t=data[i][1:]
X.append(t)
t=data[i][0]
Y.append(t)
i=1+i
X=np.asarray(X)
Y=np.asarray(Y)
le = preprocessing.LabelEncoder()
Z=le.fit_transform(Y)
clf = RandomForestClassifier(n_estimators=100,oob_score=True)
clf=clf.fit(X,Z)
a=clf.predict(X)
scores=clf.score(X,a)
print scores
http://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomForestClassifier.html
In score you send the Test Data and its actual labels, here you are passing the predicted labels itself which match the prediction hence you are
getting 1.0 score.
i see a couple things here.
you are doing clf.score(X, a)
but you should be doing clf.score(X, Z)
where Z is the true label for X
the score parameter is defined as such clf.score(X, true_labels_for_X)
you instead put the values that you predicted as y_true which dosen't make sense. since Sklearn will already run predict on X, you don't need to pass a.
Also, you can find the oobscore of by doing
print clf.oob_score_