I am new to the realm of machine learning, and I started competing in Kaggle competitions to get some practical experience. I am competing in the knowledge competition CIFAR 10- Object Recognition in Images, where you have to classify thousands of images in 10 classes,all the data I use can be found there. I tried to implement Gridsearch to optimize the parameters of my machine learning algorithm, but whenever I try to fit my classifier with my training data I get an error. I have found the function that raised the error, and it has something to do with my labels not having the right type, but I have no clue on how to solve it. The Labels I use are strings, and I preprocess them so that I can feed them to the algorithm. Am I doing something wrong there? Or perhaps something goes wrong when I split the dataset for the grid search? Frankly, I lack the experience and knowledge to solve this problem, and I could definitely use your help.
The code involved:
import glob
import os
from sklearn.svm import SVC
from sklearn import preprocessing
import pandas as pd
from sklearn import cross_validation
from sklearn import metrics
from sklearn.grid_search import GridSearchCV
def label_preprocessing(Labels):
Labels = np.array(Labels)[:,1]
le = preprocessing.LabelEncoder()
le.fit_transform(Labels)
return Labels
def model_selection(train,Labels):
parameters = {"C":[0.1,1,10,100],"gamma":[0.0001,0.001,0.01,0.1]}
X_train, X_test, y_train, y_test = cross_validation.train_test_split(train, Labels, test_size = 0.2, random_state = 0)
svm = SVC()
clf = GridSearchCV(svm,parameters)
clf = clf.fit(X_train,y_train)
print ("20 fold cv score: ",np.mean(cross_validation.cross_val_score(clf,X_test,y_test,cv = 10,scoring = "roc_auc")))
return clf
if __name__ == "__main__":
train_images = np.array(file_open(image_dir1,"*.png"))[:100]
test_images = np.array(file_open(image_dir2,"*.png"))[:100]
Labels = label_preprocessing(pd.read_csv(image_dir3)[:100])
train_set = [matrix_image(image) for image in train_images]
test_set = [matrix_image(image) for image in test_images]
train_set = np.array(train_set)
test_set = np.array(test_set)
print("selecting best model and evaluating it")
svm = model_selection(train_set,Labels)
print("predicting stuff")
result = svm.predict(test_set)
np.savetxt("submission.csv", result, fmt = "%s", delimiter = ",")
full traceback:
Traceback (most recent call last):
File "C:\Users\Abdc\workspace\final_submission\src\SVM.py", line 49, in <module>
svm = model_selection(train_set,Labels)
File "C:\Users\Abdc\workspace\final_submission\src\SVM.py", line 35, in model_selection
clf = clf.fit(X_train,y_train)
File "C:\Python27\lib\site-packages\sklearn\grid_search.py", line 707, in fit
return self._fit(X, y, ParameterGrid(self.param_grid))
File "C:\Python27\lib\site-packages\sklearn\grid_search.py", line 493, in _fit
for parameters in parameter_iterable
File "C:\Python27\lib\site-packages\sklearn\externals\joblib\parallel.py", line 517, in __call__
self.dispatch(function, args, kwargs)
File "C:\Python27\lib\site-packages\sklearn\externals\joblib\parallel.py", line 312, in dispatch
job = ImmediateApply(func, args, kwargs)
File "C:\Python27\lib\site-packages\sklearn\externals\joblib\parallel.py", line 136, in __init__
self.results = func(*args, **kwargs)
File "C:\Python27\lib\site-packages\sklearn\grid_search.py", line 311, in fit_grid_point
this_score = clf.score(X_test, y_test)
File "C:\Python27\lib\site-packages\sklearn\base.py", line 294, in score
return accuracy_score(y, self.predict(X))
File "C:\Python27\lib\site-packages\sklearn\metrics\metrics.py", line 1064, in accuracy_score
y_type, y_true, y_pred = _check_clf_targets(y_true, y_pred)
File "C:\Python27\lib\site-packages\sklearn\metrics\metrics.py", line 123, in _check_clf_targets
raise ValueError("{0} is not supported".format(y_type))
ValueError: unknown is not supported
This is the function that raised the error. It can be found in the sklearn.metrics module:
def _check_clf_targets(y_true, y_pred):
"""Check that y_true and y_pred belong to the same classification task
This converts multiclass or binary types to a common shape, and raises a
ValueError for a mix of multilabel and multiclass targets, a mix of
multilabel formats, for the presence of continuous-valued or multioutput
targets, or for targets of different lengths.
Column vectors are squeezed to 1d.
Parameters
----------
y_true : array-like,
y_pred : array-like
Returns
-------
type_true : one of {'multilabel-indicator', 'multilabel-sequences', \
'multiclass', 'binary'}
The type of the true target data, as output by
``utils.multiclass.type_of_target``
y_true : array or indicator matrix or sequence of sequences
y_pred : array or indicator matrix or sequence of sequences
"""
y_true, y_pred = check_arrays(y_true, y_pred, allow_lists=True)
type_true = type_of_target(y_true)
type_pred = type_of_target(y_pred)
y_type = set([type_true, type_pred])
if y_type == set(["binary", "multiclass"]):
y_type = set(["multiclass"])
if len(y_type) > 1:
raise ValueError("Can't handle mix of {0} and {1}"
"".format(type_true, type_pred))
# We can't have more than one value on y_type => The set is no more needed
y_type = y_type.pop()
# No metrics support "multiclass-multioutput" format
if (y_type not in ["binary", "multiclass", "multilabel-indicator",
"multilabel-sequences"]):
raise ValueError("{0} is not supported".format(y_type))
if y_type in ["binary", "multiclass"]:
y_true = column_or_1d(y_true)
y_pred = column_or_1d(y_pred)
return y_type, y_true, y_pred
Extra information about the Labels:
Content of labels and dtype:
In [21]:
Labels = np.array(Labels)[:,1]
Labels
Out[21]:
array(['frog', 'truck', 'truck', ..., 'truck', 'automobile', 'automobile'], dtype=object)
Content of labels after preprocessing
In [25]:
Labels = np.array(Labels)[:,1]
Labels
le = preprocessing.LabelEncoder()
Labels = le.fit_transform(Labels)
Labels
Out[25]:
array([6, 9, 9, ..., 9, 1, 1])
Shape of labels after preprocessing:
In [18]:
Labels = np.array(Labels)[:,1]
Labels.shape
le = preprocessing.LabelEncoder()
Labels = le.fit_transform(Labels)
Labels.shape
Out[18]:
(50000L,)
The original content can be found here: https://www.kaggle.com/c/cifar-10/data. Which contains an ID for a datapoint and its class Label. So it is a nx2 matrix.
This might be caused by issue #2374. As a workaround you can try to use Labels = Labels.astype(str).
Also, I would suggest you to follow the PEP8 code conventions to share python code with the community. In particular variable names are usually lowercase.
Related
I have the following python code that I am using after preprocessing the data where data has to columns, one is the label either positive or negative and the other has tweet texts.
X_train, X_test, y_train, y_test = train_test_split(data['Tweet'], data['Label'], test_size=0.20, random_state=0)
tf_idf = TfidfVectorizer()
x_traintf = tf_idf.fit_transform(X_train)
x_traintf = tf_idf.transform(X_train)
x_testtf = tf_idf.fit_transform(X_test)
x_testtf = tf_idf.transform(X_test)
naive_bayes_classifier = MultinomialNB()
naive_bayes_classifier.fit(x_traintf, y_train)
y_pred = naive_bayes_classifier.predict(x_testtf)
print(metrics.classification_report(y_test, y_pred, target_names=['pos', 'neg']))
Here is the full error:
Traceback (most recent call last):
File "C:\Users\Lenovo\PycharmProjects\pythonProject1\main.py", line 72, in <module>
naive_bayes_classifier.fit(x_traintf, y_train)
File "C:\Users\Lenovo\PycharmProjects\pythonProject1\venv\Lib\site-packages\sklearn\naive_bayes.py", line 749, in fit
X, y = self._check_X_y(X, y)
^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Lenovo\PycharmProjects\pythonProject1\venv\Lib\site-packages\sklearn\naive_bayes.py", line 583, in _check_X_y
return self._validate_data(X, y, accept_sparse="csr", reset=reset)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Lenovo\PycharmProjects\pythonProject1\venv\Lib\site-packages\sklearn\base.py", line 565, in _validate_data
X, y = check_X_y(X, y, **check_params)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Lenovo\PycharmProjects\pythonProject1\venv\Lib\site-packages\sklearn\utils\validation.py", line 1122, in check_X_y
y = _check_y(y, multi_output=multi_output, y_numeric=y_numeric, estimator=estimator)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Lenovo\PycharmProjects\pythonProject1\venv\Lib\site-packages\sklearn\utils\validation.py", line 1144, in _check_y
_assert_all_finite(y, input_name="y", estimator_name=estimator_name)
File "C:\Users\Lenovo\PycharmProjects\pythonProject1\venv\Lib\site-packages\sklearn\utils\validation.py", line 111, in _assert_all_finite
raise ValueError("Input contains NaN")
ValueError: Input contains NaN
I've tried this as well but got similar results:
X_train, X_test, y_train, y_test = train_test_split(all_X, all_y, test_size=0.2, random_state=42)
vectorizer = TfidfVectorizer()
X_train_tfidf = vectorizer.fit_transform(X_train)
clf = MultinomialNB()
clf.fit(X_train_tfidf, y_train)
X_test_tfidf = vectorizer.transform(X_test)
y_pred = clf.predict(X_test_tfidf)
print(metrics.accuracy_score(y_test, y_pred))
edit: I've used data.dropna(inplace=True) and it appears to think that my strings are null because they are in Arabic.
Ok, so first of all, there must be some confusion around what the methods do because they are being used wrong. There might a chance that this is the issue.
Method .fit_transform() will fit to the data but also transform in place, it is like calling fit() and then transform(). Have a look at the documentation for more clarity: https://scikit-learn.org/stable/modules/generated/sklearn.feature_extraction.text.TfidfVectorizer.html#sklearn.feature_extraction.text.TfidfVectorizer.fit_transform
Your code, for the transformation of the data, should be something like the following:
tf_idf = TfidfVectorizer()
x_traintf = tf_idf.fit_transform(X_train)
x_testtf = tf_idf.transform(X_test)
You only fit and learn the train data, and transform the train and test data with that learning. Your original code, was actually transforming the train data twice, and learning from the test data again and transforming twice also.
Do let me know if this is the issue. It might be that this double transformation caused issues. Please print the output after using the transformer, to see the output of the train and test data (features).
I am following Müller & Guido's Machine Learning with Python book, and I am trying to run classifications on this dataset.
So far my code looks like this:
import pandas as pd
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.svm import LinearSVC
# Read the Churn data into a dataset (pandas) from the cvs file
dataset = pd.read_csv(r'C:\Users\Amalie\IdeaProjects\INFO284\src\Lab2.csv')
# Make the data into a 2D NumPy array (as scikit-learn expects for the data)
dataframe = dataset[['SeniorCitizen', 'Partner', 'Dependents', 'tenure', 'PhoneService', 'MultipleLines',
'InternetService', 'OnlineSecurity', 'Churn']]
y = dataframe['Churn'] # Target
X = dataframe.drop('Churn', 1) # Features ( all other than target column 'Churn' )
# Logistic Regression
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=20) # Split into test/training sets
logReg = LogisticRegression(max_iter=100000).fit(X_train, y_train)
print("Training set score: {:.3f}".format(logReg.score(X_train, y_train)))
print("Test set score: {:.3f}".format(logReg.score(X_test, y_test)))
When I run it, I get this error:
Traceback (most recent call last):
File "C:/Users/Amalie/IdeaProjects/INFO284/src/Lab5.py", line 19, in <module>
logReg = LogisticRegression(max_iter=100000).fit(X_train, y_train)
File "C:\Users\Amalie\IdeaProjects\INFO284\venv\lib\site-packages\sklearn\linear_model\_logistic.py", line 1514, in fit
accept_large_sparse=solver not in ["liblinear", "sag", "saga"],
File "C:\Users\Amalie\IdeaProjects\INFO284\venv\lib\site-packages\sklearn\base.py", line 581, in _validate_data
X, y = check_X_y(X, y, **check_params)
File "C:\Users\Amalie\IdeaProjects\INFO284\venv\lib\site-packages\sklearn\utils\validation.py", line 976, in check_X_y
estimator=estimator,
File "C:\Users\Amalie\IdeaProjects\INFO284\venv\lib\site-packages\sklearn\utils\validation.py", line 746, in check_array
array = np.asarray(array, order=order, dtype=dtype)
File "C:\Users\Amalie\IdeaProjects\INFO284\venv\lib\site-packages\pandas\core\generic.py", line 1993, in __array__
return np.asarray(self._values, dtype=dtype)
ValueError: could not convert string to float: 'No'
Process finished with exit code 1
It says that the problem is with this line
logReg = LogisticRegression(max_iter=100000).fit(X_train, y_train)
I have used the fit()-method before when running other classification problems, but I've never come across this issue before. What am I doing wrong?
I'm trying to run a sklearn pipeline with TFIDF vectorizer and XGBoost Classifier through a GridSearchCV, but it doesn't work because of an internal error. The data is 4000 sentences, marked either true or false (1 or 0). This is the code:
import numpy as np
import pandas as pd
from gensim import utils
import gensim.parsing.preprocessing as gsp
from sklearn.pipeline import Pipeline
from sklearn.base import BaseEstimator
from sklearn.feature_extraction.text import TfidfVectorizer
import xgboost as xgb
from sklearn.model_selection import GridSearchCV
from sklearn.metrics import f1_score
train = pd.read_csv("train_data.csv")
test = pd.read_csv("test_data.csv")
train_x = train.iloc[:, 0]
train_y = train.iloc[:, 1]
test_x = test.iloc[:, 0]
test_y = test.iloc[:, 1]
folds = 4
xgb_parameters = {
'xgboost__n_estimators': [1000, 1500],
'xgboost__max_depth': [12, 15],
'xgboost__learning_rate': [0.1, 0.12],
'xgboost__objective': ['binary:logistic']
}
model = Pipeline(steps=[('tfidf', TfidfVectorizer()),
('xgboost', xgb.XGBClassifier())])
gs_cv = GridSearchCV(estimator=model,
param_grid=xgb_parameters,
n_jobs=1,
refit=True,
cv=2,
scoring=f1_score)
gs_cv.fit(train_x, train_y)
But I am getting an error:
>>> gs_cv.fit(train_x, train_y)
C:\Users\draga\miniconda3\lib\site-packages\xgboost\sklearn.py:888: UserWarning: The use of label encoder in XGBClassifier is deprecated and will be removed in a future release. To remove this warning, do the following: 1) Pass option use_label_encoder=False when constructing XGBClassifier object; and 2) Encode your labels (y) as integers starting with 0, i.e. 0, 1, 2, ..., [num_class - 1].
[21:31:18] WARNING: C:/Users/Administrator/workspace/xgboost-win64_release_1.3.0/src/learner.cc:1061: Starting in XGBoost 1.3.0, the default evaluation metric used with the objective 'binary:logistic' was changed from 'error' to 'logloss'. Explicitly set eval_metric if you'd like to restore the old behavior.
C:\Users\draga\miniconda3\lib\site-packages\sklearn\utils\validation.py:70: FutureWarning: Pass labels=0 0
1 1
2 1
3 0
4 1
..
2004 0
2005 0
2008 0
2009 0
2012 0
Name: Bad Sentence, Length: 2000, dtype: int64 as keyword args. From version 1.0 (renaming of 0.25) passing these as positional arguments will result in an error
warnings.warn(f"Pass {args_msg} as keyword args. From version "
C:\Users\draga\miniconda3\lib\site-packages\sklearn\model_selection\_validation.py:683: UserWarning: Scoring failed. The score on this train-test partition for these parameters will be set to nan. Details:
Traceback (most recent call last):
File "C:\Users\draga\miniconda3\lib\site-packages\sklearn\model_selection\_validation.py", line 674, in _score
scores = scorer(estimator, X_test, y_test)
File "C:\Users\draga\miniconda3\lib\site-packages\sklearn\utils\validation.py", line 74, in inner_f
return f(**kwargs)
File "C:\Users\draga\miniconda3\lib\site-packages\sklearn\metrics\_classification.py", line 1068, in f1_score
return fbeta_score(y_true, y_pred, beta=1, labels=labels,
File "C:\Users\draga\miniconda3\lib\site-packages\sklearn\utils\validation.py", line 63, in inner_f
return f(*args, **kwargs)
File "C:\Users\draga\miniconda3\lib\site-packages\sklearn\metrics\_classification.py", line 1192, in fbeta_score
_, _, f, _ = precision_recall_fscore_support(y_true, y_pred,
File "C:\Users\draga\miniconda3\lib\site-packages\sklearn\utils\validation.py", line 63, in inner_f
return f(*args, **kwargs)
File "C:\Users\draga\miniconda3\lib\site-packages\sklearn\metrics\_classification.py", line 1461, in precision_recall_fscore_support
labels = _check_set_wise_labels(y_true, y_pred, average, labels,
File "C:\Users\draga\miniconda3\lib\site-packages\sklearn\metrics\_classification.py", line 1274, in _check_set_wise_labels
y_type, y_true, y_pred = _check_targets(y_true, y_pred)
File "C:\Users\draga\miniconda3\lib\site-packages\sklearn\metrics\_classification.py", line 83, in _check_targets
check_consistent_length(y_true, y_pred)
File "C:\Users\draga\miniconda3\lib\site-packages\sklearn\utils\validation.py", line 259, in check_consistent_length
lengths = [_num_samples(X) for X in arrays if X is not None]
File "C:\Users\draga\miniconda3\lib\site-packages\sklearn\utils\validation.py", line 259, in <listcomp>
lengths = [_num_samples(X) for X in arrays if X is not None]
File "C:\Users\draga\miniconda3\lib\site-packages\sklearn\utils\validation.py", line 192, in _num_samples
raise TypeError(message)
TypeError: Expected sequence or array-like, got <class 'sklearn.pipeline.Pipeline'>
What could be the problem?
Do I need to include the transform method for TfidfVectorizer() in the pipeline?
The main problem is your scoring parameter for the search. Scorers for hyperparameter tuners in sklearn need to have the signature (estimator, X, y). You can use the make_scorer convenience function, or in this case just pass the name as a string, scorer="f1".
See the docs, the list of builtins and information on signatures.
(You do not need to explicitly use the transform method; that's handled internally by the pipeline.)
I am trying to find the score of a given data set with respect to some training data. I have written the following code:
from sklearn.ensemble import RandomForestClassifier
import numpy as np
randomForest = RandomForestClassifier(n_estimators = 200)
li_train1 = [[1,2,3,4,5,6,7,8,9],[1,2,3,4,5,6,7,8,9]]
li_train2 = [[1,2,3,4,5,6,7,8,9],[1,2,3,4,5,6,7,8,9]]
li_text1 = [[10,20,30,40,50,60,70,80,90], [10,20,30,40,50,60,70,80,90]]
li_text2 = [[1,2,3,4,5,6,7,8,9],[1,2,3,4,5,6,7,8,9]]
randomForest.fit(li_train1, li_train2)
output = randomForest.score(li_train1, li_text1)
On compiling and trying to run the program I am getting the error:
Traceback (most recent call last):
File "trial.py", line 16, in <module>
output = randomForest.score(li_train1, li_text1)
File "/usr/local/lib/python2.7/dist-packages/sklearn/base.py", line 349, in score
return accuracy_score(y, self.predict(X), sample_weight=sample_weight)
File "/usr/local/lib/python2.7/dist-packages/sklearn/metrics/classification.py", line 172, in accuracy_score
y_type, y_true, y_pred = _check_targets(y_true, y_pred)
File "/usr/local/lib/python2.7/dist-packages/sklearn/metrics/classification.py", line 89, in _check_targets
raise ValueError("{0} is not supported".format(y_type))
ValueError: multiclass-multioutput is not supported
On checking the documentation related to the score method it says:
score(X, y, sample_weight=None)
X : array-like, shape = (n_samples, n_features)
Test samples.
y : array-like, shape = (n_samples) or (n_samples, n_outputs)
True labels for X.
Both X and y in my case are arrays, 2d arrays.
I also went through this question but I couldn't understand where am I going wrong.
EDIT
So as per the answer and the comments that follow, I have edited the program as follows:
from sklearn.ensemble import RandomForestClassifier
from sklearn.preprocessing import MultiLabelBinarizer
import numpy as np
randomForest = RandomForestClassifier(n_estimators = 200)
mlb = MultiLabelBinarizer()
li_train1 = [[1,2,3,4,5,6,7,8,9],[1,2,3,4,5,6,7,8,9]]
li_train2 = [[1,2,3,4,5,6,7,8,9],[1,2,3,4,5,6,7,8,9]]
li_text1 = [100,200]
li_text2 = [[1,2,3,4,5,6,7,8,9],[1,2,3,4,5,6,7,8,9]]
randomForest.fit(li_train1, li_train2)
output = randomForest.score(li_train1, li_text1)
After this edit I am getting the error:
Traceback (most recent call last):
File "trial.py", line 19, in <module>
output = randomForest.score(li_train1, li_text1)
File "/usr/local/lib/python2.7/dist-packages/sklearn/base.py", line 349, in score
return accuracy_score(y, self.predict(X), sample_weight=sample_weight)
File "/usr/local/lib/python2.7/dist-packages/sklearn/metrics/classification.py", line 172, in accuracy_score
y_type, y_true, y_pred = _check_targets(y_true, y_pred)
File "/usr/local/lib/python2.7/dist-packages/sklearn/metrics/classification.py", line 82, in _check_targets
"".format(type_true, type_pred))
ValueError: Can't handle mix of binary and multiclass-multioutput
According to the documentation:
Warning: At present, no metric in sklearn.metrics supports the multioutput-multiclass classification task.
The score method invokes sklearn's accuracy metric but this isn't supported for the multi-class, multi-output classification problem you've defined.
It's not clear from your question if you really intend to solve a multi-class, multi-output problem. If that's not your intention, then you should restructure your input arrays.
If on the other hand you really want to solve this kind of problem, you'll simply need to define your own scoring function.
UPDATE
Since you are not solving a multi-class, multi-label problem you should restructure your data so that it looks something like this:
from sklearn.ensemble import RandomForestClassifier
# training data
X = [
[1,2,3,4,5,6,7,8,9],
[1,2,3,4,5,6,7,8,9]
]
y = [0,1]
# fit the model
randomForest.fit(X,y)
# test data
Xtest = [
[1,2,0,4,5,6,0,8,9],
[1,1,3,1,5,0,7,8,9]
]
ytest = [0,1]
output = randomForest.score(Xtest,ytest)
print(output) # 0.5
Here is data files here and here. You can download it by clicking on links the link. I am using Pandas, Numpy and Python3.
Here is my code:
import pandas as pa
import numpy as nu
from sklearn.linear_model import Perceptron
from sklearn.metrics import accuracy_score
from sklearn.preprocessing import StandardScaler
def get_accuracy(X_train, y_train, X_test, y_test):
perceptron = Perceptron()
perceptron.fit(X_train, y_train)
perceptron.transform(X_train)
prediction = perceptron.predict(X_test)
result = accuracy_score(y_test, prediction)
return result
test_data = pa.read_csv("C:/Users/Roman/Downloads/perceptron-test.csv")
test_data.columns = ["class", "f1", "f2"]
train_data = pa.read_csv("C:/Users/Roman/Downloads/perceptron-train.csv")
train_data.columns = ["class", "f1", "f2"]
scaler = StandardScaler()
scaler.fit_transform(train_data[train_data.columns[1:]]).reshape(-1,1)
X_train = scaler.transform(train_data[train_data.columns[1:]])
scaler.fit_transform(train_data[train_data.columns[0]])
y_train = scaler.transform(train_data[train_data.columns[0]])
scaler.fit_transform(test_data[test_data.columns[1:]])
X_test = scaler.transform(test_data[test_data.columns[1:]])
scaler.fit_transform(test_data[test_data.columns[0]])
y_test = scaler.transform(test_data[test_data.columns[0]])
scaled_accuracy = get_accuracy(nu.ravel(X_train), nu.ravel(y_train), nu.ravel(X_test), nu.ravel(y_test))
print(scaled_accuracy)
And here is error that I get:
Traceback (most recent call last):
File "C:/Users/Roman/PycharmProjects/data_project-1/lecture_2_perceptron.py", line 33, in <module>
scaled_accuracy = get_accuracy(nu.ravel(X_train), nu.ravel(y_train), nu.ravel(X_test), nu.ravel(y_test))
File "C:/Users/Roman/PycharmProjects/data_project-1/lecture_2_perceptron.py", line 9, in get_accuracy
perceptron.fit(X_train, y_train)
File "C:\Users\Roman\AppData\Roaming\Python\Python35\site-packages\sklearn\linear_model\stochastic_gradient.py", line 545, in fit
sample_weight=sample_weight)
File "C:\Users\Roman\AppData\Roaming\Python\Python35\site-packages\sklearn\linear_model\stochastic_gradient.py", line 389, in _fit
X, y = check_X_y(X, y, 'csr', dtype=np.float64, order="C")
File "C:\Users\Roman\AppData\Roaming\Python\Python35\site-packages\sklearn\utils\validation.py", line 520, in check_X_y
check_consistent_length(X, y)
File "C:\Users\Roman\AppData\Roaming\Python\Python35\site-packages\sklearn\utils\validation.py", line 176, in check_consistent_length
"%s" % str(uniques))
**ValueError: Found arrays with inconsistent numbers of samples: [ 1 299]**
Without scaling data everything work fine. But after scaling not.
You should not call fit_transform each time you use scaler. You should fit it once, on the training data, and later only transform, otherwise you get different representation for training and testing (leading to error provided). There is also no point in scaling labels.