Develop Reference

how to use cross-validation with ktrain?

I am using the ktrain package to perform multiclass text classification. The example on the official ktrain website works great (https://github.com/amaiya/ktrain)
categories = ['alt.atheism', 'soc.religion.christian','comp.graphics', 'sci.med']
from sklearn.datasets import fetch_20newsgroups
train_b = fetch_20newsgroups(subset='train', categories=categories, shuffle=True)
test_b = fetch_20newsgroups(subset='test',categories=categories, shuffle=True)
(x_train, y_train) = (train_b.data, train_b.target)
(x_test, y_test) = (test_b.data, test_b.target)
# build, train, and validate model (Transformer is wrapper around transformers library)
import ktrain
from ktrain import text
MODEL_NAME = 'distilbert-base-uncased'
t = text.Transformer(MODEL_NAME, maxlen=500, class_names=train_b.target_names)
trn = t.preprocess_train(x_train, y_train)
val = t.preprocess_test(x_test, y_test)
model = t.get_classifier()
learner = ktrain.get_learner(model, train_data=trn, val_data=val, batch_size=6)
learner.fit_onecycle(5e-5, 4)
learner.validate(class_names=t.get_classes())
Accuracy is pretty high.
However, I am comparing this model with other models trained with scikit-learn and, in particular, the other models' accuracy is assessed using cross validation
cross_val_score(sgd_clf, X_train, y_train, cv=3, scoring="accuracy")
How can I adapt the code above to make sure the transformer model used with ktrain is also evaluated with the same cross validation methodology?

You can try something like this:
from ktrain import text
import ktrain
import pandas as pd
from sklearn.model_selection import train_test_split,KFold
from sklearn.metrics import accuracy_score
from sklearn.datasets import fetch_20newsgroups
# load text data
categories = ['alt.atheism', 'soc.religion.christian','comp.graphics', 'sci.med']
train_b = fetch_20newsgroups(subset='train', categories=categories, shuffle=True)
test_b = fetch_20newsgroups(subset='test',categories=categories, shuffle=True)
(x_train, y_train) = (train_b.data, train_b.target)
(x_test, y_test) = (test_b.data, test_b.target)
df = pd.DataFrame({'text':x_train, 'target': [train_b.target_names[y] for y in y_train]})
# CV with transformers
N_FOLDS = 2
EPOCHS = 3
LR = 5e-5
def transformer_cv(MODEL_NAME):
predictions,accs=[],[]
data = df[['text', 'target']]
for train_index, val_index in KFold(N_FOLDS).split(data):
preproc = text.Transformer(MODEL_NAME, maxlen=500)
train,val=data.iloc[train_index],data.iloc[val_index]
x_train=train.text.values
x_val=val.text.values
y_train=train.target.values
y_val=val.target.values
trn = preproc.preprocess_train(x_train, y_train)
model = preproc.get_classifier()
learner = ktrain.get_learner(model, train_data=trn, batch_size=16)
learner.fit_onecycle(LR, EPOCHS)
predictor = ktrain.get_predictor(learner.model, preproc)
pred=predictor.predict(x_val)
acc=accuracy_score(y_val,pred)
print('acc',acc)
accs.append(acc)
return accs
print( transformer_cv('distilbert-base-uncased') )
# output:
# [0.9627989371124889, 0.9689716312056738]
REFERENCE: See this Kaggle notebook for a regression example.

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()

Get panda Series from csv

I am totally new to machine learning, I am currently playing with MNIST machine learning, using RandomForestClassifier.
I use sklearn and panda.
I have a training CSV data set.
import pandas as pd
import numpy as np
from sklearn import model_selection
from sklearn.ensemble import RandomForestClassifier
from sklearn.svm import LinearSVC
from sklearn.linear_model import SGDClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import accuracy_score
train = pd.read_csv("train.csv")
features = train.columns[1:]
X = train[features]
y = train['label']
user_train = pd.read_csv("input.csv")
user_features = user_train.columns[1:]
y_train = user_train[user_features]
user_y = user_train['label']
X_train, X_test, y_train, y_test = model_selection.train_test_split(X/255.,y,test_size=1,random_state=0)
clf_rf = RandomForestClassifier()
clf_rf.fit(X_train, y_train)
y_pred_rf = clf_rf.predict(X_test)
acc_rf = accuracy_score(y_test, y_pred_rf)
print("pred : ", y_pred_rf)
print("random forest accuracy: ",acc_rf)
I have the current code, which works well. It takes the training set, split and take one element for testing, and does the prediction.
What I want now is to use the testing data from an input, I have a new csv called "input.csv", and I want to predict the value inside this csv.
How can I replace the model_selection.train_test_split with my input data ?
I am sure the response is very obvious, and I didn't find anything.

The following part of your code is unused
user_train = pd.read_csv("input.csv")
user_features = user_train.columns[1:]
y_train = user_train[user_features]
user_y = user_train['label']
If input.csv has the same structure of train.csv you may want to:
train a classifier and test it on a split of the input.csv dataset: (please refer to http://scikit-learn.org/stable/modules/generated/sklearn.model_selection.train_test_split.html to know how to set the test size)
input_train = pd.read_csv("input.csv")
input_features = user_train.columns[1:]
input_data = user_train[input_features]
input_labels = user_train['label']
data_train, data_test, labels_train, labels_test = model_selection.train_test_split(input_data/255.,input_labels,test_size=1,random_state=0)
clf_rf = RandomForestClassifier()
clf_rf.fit(data_train, labels_train)
labels_pred_rf = clf_rf.predict(data_test)
acc_rf = accuracy_score(labels_test, labels_pred_rf)
test the previously trained classifier on the whole input.csv file
input_train = pd.read_csv("input.csv")
input_features = user_train.columns[1:]
input_data = user_train[input_features]
input_labels = user_train['label']
labels_pred_rf = clf_rf.predict(input_data)
acc_rf = accuracy_score(input_labels, labels_pred_rf)

sklearn support vector machine is not learning

I am trying to classify images using sklearn's svm.SVC classifier, but it's not learning, after training I got 0.1 accuracy (there are 10 classes, so 0.1 accuracy is the same as a random guess)
I am using the CIFAR-10 datatset. 10000 images that are represented as 3072 uint8s. The first 1024 are the red pixels, the second 1024 are the green pixels and the thirst 1024 are the blue pixels.
Each image also has a label, which is a number 0-9
Here is my code:
import numpy as np
from sklearn import preprocessing, svm
import pandas as pd
import pickle
from sklearn.externals import joblib
train_data = pickle.load(open('data_batch_1','rb'), encoding='latin1')
test_data = pickle.load(open('test_batch','rb'), encoding='latin1')
X_train = np.array(train_data['data'])
y_train = np.array(train_data['labels'])
X_test = np.array(test_data['data'])
y_test = np.array(test_data['labels'])
clf = svm.SVC(verbose=True)
clf.fit(X_train, y_train)
accuracy = clf.score(X_test, y_test)
joblib.dump(clf, 'Cifar-10-clf.pickle')
print(accuracy)
Does anyone know what my problem could be or can point me to resources to solve this?

I'm not sure but I think that you need to tune the parameters of SVC.
I tested some parameters for learning then I got an 0.318 accuracy.
here is code:
# coding: utf-8
import numpy as np
from sklearn import preprocessing, svm
import cPickle
train_data = cPickle.load(open('data/data_batch_1', 'rb'))
test_data = cPickle.load(open('data/test_batch', 'rb'))
X_train = np.array(train_data['data'])
y_train = np.array(train_data['labels'])
X_test = np.array(test_data['data'][:1000])
y_test = np.array(test_data['labels'][:1000])
clf = svm.SVC(kernel='linear', C=10, gamma=0.01)
clf.fit(X_train, y_train)
accuracy = clf.score(X_test, y_test)
print "Accuracy: ", accuracy
And I recommend grid search function for auto tuning the hyper-parameters.
This is public documents about tuning the hyper-parameters in scikit-learn

How to do regression using tensorflow with series output?

I want to build a regression model with 2 output nodes using tensorflow. I search a code which can build regression model but with 1 output nodes.
https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/skflow/boston.py
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from sklearn import cross_validation
from sklearn import metrics
from sklearn import preprocessing
import tensorflow as tf
from tensorflow.contrib import learn
def main(unused_argv):
# Load dataset
boston = learn.datasets.load_dataset('boston')
x, y = boston.data, boston.target
# Split dataset into train / test
x_train, x_test, y_train, y_test = cross_validation.train_test_split(
x, y, test_size=0.2, random_state=42)
# Scale data (training set) to 0 mean and unit standard deviation.
scaler = preprocessing.StandardScaler()
x_train = scaler.fit_transform(x_train)
# Build 2 layer fully connected DNN with 10, 10 units respectively.
feature_columns = learn.infer_real_valued_columns_from_input(x_train)
regressor = learn.DNNRegressor(
feature_columns=feature_columns, hidden_units=[10, 10])
# Fit
regressor.fit(x_train, y_train, steps=5000, batch_size=1)
# Predict and score
y_predicted = list(
regressor.predict(scaler.transform(x_test), as_iterable=True))
score = metrics.mean_squared_error(y_predicted, y_test)
print('MSE: {0:f}'.format(score))
if __name__ == '__main__':
tf.app.run()
I am new to tensorflow, so I searched for the code which has similarity to how mine works, but the output of the code is one.
In my model, the input is N*1000, and the output is N*2. I wonder are there effective and efficient code for regression. Please give me some example.

Actually, I find a workable code using DNNRegressor:
import numpy as np
from sklearn.cross_validation import train_test_split
from tensorflow.contrib import learn
import tensorflow as tf
import logging
#logging.getLogger().setLevel(logging.INFO)
#Some fake data
N=200
X=np.array(range(N),dtype=np.float32)/(N/10)
X=X[:,np.newaxis]
#Y=np.sin(X.squeeze())+np.random.normal(0, 0.5, N)
Y = np.zeros([N,2])
Y[:,0] = X.squeeze()
Y[:,1] = X.squeeze()**2
X_train, X_test, Y_train, Y_test = train_test_split(X, Y,
train_size=0.8,
test_size=0.2)
reg=learn.DNNRegressor(hidden_units=[10,10])
reg.fit(X_train,Y_train[:,0],steps=500)
But, this code will work only if the shape of Y_train is N*1, and it will fail when the shape of Y_train is N*2.
However, I want to build a regress model and the input is N*1000, the output is N*2. And I can't fix it.