Explication cross_val_score scikit_learn parameter cv - python

I don't understand why i have different result in this configuration of cross_val_score
and a simple model.
from sklearn.datasets import load_iris
from sklearn.utils import shuffle
from sklearn import tree
import numpy as np
np.random.seed(1234)
iris = load_iris()
X, y = iris.data, iris.target
X,y = shuffle(X,y)
print(y)
clf = tree.DecisionTreeClassifier(max_depth=2,class_weight={2: 0.3, 1: 10,0:0.3},random_state=1234)
clf2 = clf.fit(X, y)
tree.plot_tree(clf2)
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
predi = clf2.predict(X)
cm = confusion_matrix(y_true=y, y_pred=predi)
print(cm)
print("Accuracy = ",round(accuracy_score(y,predi)* 100.0,2))
from sklearn.model_selection import cross_val_score,cross_val_predict
max_id = len(X)
limit = round(max_id*0.6,0)
min_id=0
train = np.arange(0,limit)
test = np.arange(limit,max_id)
test = [int(x) for x in test]
train = [int(x) for x in train]
print(train)
print(test)
predi = cross_val_score(clf,X,y,cv=[(train,test)])
print(predi)
train = X[train[0]:train[-1]]
y_train = y[train[0]:train[-1]]
Xtest = X[test[0]:test[-1]]
y_test = y[test[0]:test[-1]]
clf3 = clf.fit(Xtrain,y_train)
predi = clf3.predict(Xtest)
cm = confusion_matrix(y_true=y_test, y_pred=predi)
print(cm)
print("Accuracy = ",round(accuracy_score(y_test,predi)* 100.0,2))
I don't understand why i have different accuracy whereas i have the same parameters en the same train test sample

Basically, the kind of data split you use will have an impact on your model accuracy. This is well documented in machine learning field. Secondly, your first model is strictly biased as you have used your training set for testing which will result in ~100% accuracy.
https://www.analyticsvidhya.com/blog/2021/05/4-ways-to-evaluate-your-machine-learning-model-cross-validation-techniques-with-python-code/
https://towardsdatascience.com/train-test-split-c3eed34f763b

Related

Poor accuarcy score for Semi-Supervised Support Vector machine

I am using a Semi-Supervised approach for Support Vector Machine in Python for the image classification from PASCAL VOC 2007 data.
I have tried with the default parameters from the libraries and also tuned them but it get extremely bad accuracy of about only ~ 2%.
Below is my code:
import pandas as pd
import numpy as np
from sklearn import decomposition
from sklearn.model_selection import train_test_split
from numpy import concatenate
import numpy as np
from sklearn import datasets
from sklearn import metrics
from sklearn.model_selection import train_test_split
from sklearn import svm
from sklearn import decomposition
import warnings
warnings.filterwarnings("ignore")
color_layout_features = pd.read_pickle("color_layout_descriptor.pkl")
bow_surf = pd.read_pickle("bow_surf.pkl")
color_hist_features = pd.read_pickle("hist.pkl")
labels = pd.read_pickle("labels.pkl")
# Feat. Scaling
def scale(X, x_min, x_max):
nom = (X-X.min(axis=0))*(x_max-x_min)
denom = X.max(axis=0) - X.min(axis=0)
denom[denom==0] = 1
return x_min + nom/denom
# normalization
def normalize(x):
return (x - np.min(x))/(np.max(x) - np.min(x))
color_layout_features_scaled = scale(color_layout_features, 0, 1)
color_hist_features_scaled = scale(color_hist_features, 0, 1)
bow_surf_scaled = scale(bow_surf, 0, 1)
features = np.hstack([color_layout_features_scaled, color_hist_features_scaled, bow_surf_scaled])
# define dataset
X, Y = features, labels
X = normalize(X)
pca = decomposition.PCA(n_components=100)
pca.fit(X)
X = pca.transform(X)
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.30, random_state=1, stratify=Y)
# split train into labeled and unlabeled
X_train_lab, X_test_unlab, y_train_lab, y_test_unlab = train_test_split(X_train, y_train, test_size=0.30, random_state=1, stratify=y_train)
# create the training dataset input
X_train_mixed = concatenate((X_train_lab, X_test_unlab))
# create "no label" for unlabeled data
nolabel = [-1 for _ in range(len(y_test_unlab))]
# recombine training dataset labels
y_train_mixed = concatenate((y_train_lab, nolabel))
from semisupervised import S3VM
model = S3VM(kernel="Linear", C = 1e-2, gamma = 0.5, lamU = 1.0, probability=True)
#model.fit(X_train_mixed, _train_mixed)
model.fit(np.vstack((X_train_lab, X_test_unlab)), np.append(y_train_lab, nolabel))
#model.fit(np.vstack((label_X_train, unlabel_X_train)), np.append(label_y_train, unlabel_y))
# predict
predict = model.predict(X_test)
acc = metrics.accuracy_score(y_test, predict)
# metric
print("accuracy", acc*100)
accuracy 2.6692291266282298
I am using a Transductive version of SVM (TSVM) from the semisupervised library. But not sure what am I doing wrong so that even after tweaking the parameters I still get the same result. Any inputs would be helpful.
I refer https://github.com/rosefun/SemiSupervised/blob/master/semisupervised/TSVM.py to make the implementation. Any inputs would be helpful.
Please consider that according to link Documentation "The unlabeled samples should be labeled as -1".

Calculating AUC for LogisticRegression model

Let's take data
import numpy as np
import pandas as pd
from sklearn.datasets import load_breast_cancer
from sklearn.decomposition import PCA
from sklearn import datasets
from sklearn.preprocessing import StandardScaler
from sklearn import metrics
data = load_breast_cancer()
X = data.data
y = data.target
I want to create model using only first principal component and calculate AUC for it.
My work so far
scaler = StandardScaler()
scaler.fit(X_train)
X_scaled = scaler.transform(X)
pca = PCA(n_components=1)
principalComponents = pca.fit_transform(X)
principalDf = pd.DataFrame(data = principalComponents
, columns = ['principal component 1'])
clf = LogisticRegression()
clf = clf.fit(principalDf, y)
pred = clf.predict_proba(principalDf)
But while I'm trying to use
fpr, tpr, thresholds = metrics.roc_curve(y, pred, pos_label=2)
Following error occurs :
y should be a 1d array, got an array of shape (569, 2) instead.
I tried to reshape my data
fpr, tpr, thresholds = metrics.roc_curve(y.reshape(1,-1), pred, pos_label=2)
But it didn't solve the issue (it outputs) :
multilabel-indicator format is not supported
Do you have any idea how can I perform AUC on this first principal component?
You may wish to try:
from sklearn.datasets import load_breast_cancer
from sklearn.decomposition import PCA
from sklearn import datasets
from sklearn.preprocessing import StandardScaler
from sklearn import metrics
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
X,y = load_breast_cancer(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X,y)
scaler = StandardScaler()
pca = PCA(2)
clf = LogisticRegression()
ppl = Pipeline([("scaler",scaler),("pca",pca),("clf",clf)])
ppl.fit(X_train, y_train)
preds = ppl.predict(X_test)
fpr, tpr, thresholds = metrics.roc_curve(y_test, preds, pos_label=1)
metrics.plot_roc_curve(ppl, X_test, y_test)
The problem is that predict_proba returns a column for each class. Generally with binary classification, your classes are 0 and 1, so you want the probability of the second class, so it's quite common to slice as follows (replacing the last line in your code block):
pred = clf.predict_proba(principalDf)[:, 1]

Trying to implement XGBoost into my Artificial Neural Network

I'm completely unaware as to why i'm receiving this error. I am trying to implement XGBoost but it returns with error "ValueError: For a sparse output, all columns should be a numeric or convertible to a numeric." Even after i've One Hot Encoded my categorical data. If anyone knows what is causing this and a possible solution i'd greatly appreciate it. Here is my code written in Python:
# Artificial Neural Networks - With XGBoost
# PRE PROCESS
# Importing the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
# Importing the dataset
dataset = pd.read_csv('Churn_Modelling.csv')
X = dataset.iloc[:, 3:13].values
y = dataset.iloc[:, 13].values
# Encoding Categorical Data
from sklearn.preprocessing import OneHotEncoder
from sklearn.compose import ColumnTransformer
ct = ColumnTransformer([('encoder', OneHotEncoder(), [1, 2])],
remainder = 'passthrough')
X = np.array(ct.fit_transform(X), dtype = np.float)
# Splitting the dataset into the Training set and Test set
from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.20, random_state = 0)
# Fitting XGBoost to the training set
from xgboost import XGBClassifier
classifier = XGBClassifier()
classifier.fit(x_train, y_train)
# Predicting the Test set Results
y_pred = classifier.predict(x_test)
# Making the Confusion Matrix
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)
# Applying k-Fold Cross Validation
from sklearn.model_selection import cross_val_score
accuracies = cross_val_score(estimator = classifier, X = X_train, y = y_train, cv = 10)
accuracies.mean()
accuracies.std()

100% accuracy in random forest and 94% accuracy in KNN?

I was going to classify into the following dataset.
Dataset
I achieved amazingly high results (too high) and I think I had to do something wrong.
I'm trying to make a clasification for the age group based on the rest of the characteristics. I know there is a large correlation between variables and I will have to fix it all but for now I wanted to use everything as dependent variables.
Here is the code:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
dataset = pd.read_csv('abalone.csv')
X = dataset.iloc[:, :-1].values
y = dataset.iloc[:, -1:].values
dataset["Sex"]= dataset["Sex"].replace('M', 0)
dataset["Sex"]= dataset["Sex"].replace('F', 1)
dataset["Sex"]= dataset["Sex"].replace('I', 2)
dataset["Age group"]= dataset["Age group"].replace('young abalone', 0)
dataset["Age group"]= dataset["Age group"].replace('middle-aged abalone', 1)
dataset["Age group"]= dataset["Age group"].replace('mature abalone', 2)
dataset["Age group"]= dataset["Age group"].replace('senior abalone', 3)
dataset['Age group'] = dataset['Age group'].astype(int).astype(float)
dataset['Rings'] = dataset['Rings'].astype(int).astype(float)
dataset['Sex'] = dataset['Sex'].astype(int).astype(float)
X = dataset.iloc[:, :-1].values
y = dataset.iloc[:, -1:].values
# Encoding categorical data
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder = LabelEncoder()
X[:, 0] = labelencoder.fit_transform(X[:, 0])
onehotencoder = OneHotEncoder(categorical_features = [0])
X = onehotencoder.fit_transform(X).toarray()
# Avoiding the Dummy Variable Trap
X = X[:, 1:]
# Splitting the dataset into the Training set and Test set
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 0)
# Feature Scaling
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
# Fitting Random Forest Classification to the Training set
from sklearn.ensemble import RandomForestClassifier
classifier = RandomForestClassifier(n_estimators = 10, criterion = 'entropy', random_state = 0)
classifier.fit(X_train, y_train)
# Predicting the Test set results
y_pred = classifier.predict(X_test)
# Making the Confusion Matrix
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)
cm
## KNN
# Fitting K-NN to the Training set
from sklearn.neighbors import KNeighborsClassifier
classifier2 = KNeighborsClassifier(n_neighbors = 7, metric = 'minkowski', p = 2)
classifier2.fit(X_train, y_train)
# Predicting the Test set results
y_pred = classifier2.predict(X_test)
# Making the Confusion Matrix
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)
cm
I put all the code because I don't know exactly what went wrong.
I haven't checked yet other accuracy measures because the confusion matrix itself says something probably went wrong

Scikit-Learn: Adjust train_size or test_size?

This is a question regarding best practices for sklearn.
While experimenting with SVMs using the iris dataset provided in the sklearn library. While using train_test_split, I was wondering which parameter to adjust to avoid overfitting. I was taught to adjust test_size (roughly to ~0.3), but there is a train_size parameter. Would it not make sense to adjust the train_size to avoid overfitting, or am I misunderstanding something here?
I get similar results regardless of which parameter I adjust, but I don't know if that's always the case.
Appreciate any help. Thanks!
Here is the code I am currently working with:
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.datasets import load_iris
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split as tts
from sklearn.model_selection import GridSearchCV
from sklearn.svm import SVC
from sklearn.metrics import confusion_matrix, classification_report
iris = load_iris()
df = pd.DataFrame(data=iris.data, columns=iris.feature_names)
scaler = StandardScaler()
scaler.fit(df)
scaled_df = scaler.transform(df)
df = pd.DataFrame(data=scaled_df, columns=iris.feature_names)
x = df
y = iris.target
#test_size is used here, but is swapped with train_size to experiment
x_train, x_test, y_train, y_test = tts(x, y, test_size=0.33)
c_param = np.arange(1, 100, 10)
gamma_param = np.arange(0.0001, 1, 0.001)
params = {'C':c_param, 'gamma':gamma_param}
grid = GridSearchCV(estimator=SVC(), param_grid=params, verbose=0)
grid_fit = grid.fit(x_train, y_train)
grid_pred = grid.predict(x_test)
print(grid.best_params_)
print('\n')
print("Number of training records: ", len(x_train))
print("Number of test records: ", len(x_test))
print('\n')
print(classification_report(y_true=y_test, y_pred=grid_pred))
print('\n')
print(confusion_matrix(y_true=y_test, y_pred=grid_pred))

Categories

Resources