CODEWITHSUNDEEP
pythonmachine-learningscikit-learnnaivebayes
user3486773
user3486773

Reputation: 1246

Python machine learning error... how to solve?

Not sure how to best word the title, so my apologies...

I am new to Python Machine Learning and still learning myself. I have this data set (ML_TEST):

  Sale ID   Amount in $ Region      Product  Salesperson    Win_Lose
   1            500     North       ink             Jon     1
   2            250     North       ink             Jon     0
   3            250     North       ink             Jon     0
   4            750     North       paper           Jon     0
   5            800     North       ink             Bill    0
   6            250     North       paper           Bill    1
   7            750     North       paper           Jon     1
   8            250     North       ink             Bill    1
   9            250     North       paper           Dave    0
   10           800     North       desk chair      Bill    1
   11           750     South       paper           Dave    0
   12           500     South       desk chair      Dave    1
   13           500     South       ink             Bill    1
   14           500     South       ink             Bill    0
   15           400     South       paper           Jon     0
   16           250     South       paper           Jon     0
   17           250     South       ink             Jon     1
   18           250     East        ink             Dave    1
   19           250     East        ink             Bill    1
   20           400     East        ink             Jon     0
   21           400     East        paper           Dave    1
   22           500     West        desk chair      Bill    0
   23           750     West        desk chair      Jon     1
   24           800     West        desk chair      Jon     0
   25           450     West        paper           Jon     0
   26           250     West        ink             Dave    1
   27           250     West        paper           Dave    1
   28           250     West        paper           Bill    1
   29           250     West        paper           Bill    0
   30           400     West        ink             Bill    1

And I am trying to understand the error I get when I run this:

#Load Libraries
import pandas
from pandas.tools.plotting import scatter_matrix
import matplotlib.pyplot as plt
from sklearn import model_selection
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC
import pyodbc
conn = pyodbc.connect('')

sql = "Select * from TMP.ML_TEST"
dataset = pd.read_sql(sql, conn)

array = dataset.values
X = array[:,0:5]
Y = array[:,5]
validation_size = 0.20
seed = 7
X_train, X_validation, Y_train, Y_validation = model_selection.train_test_split(X, Y, test_size=validation_size, random_state=seed)
print(Y)

seed = 7
scoring = 'accuracy'


models = []
models.append(('LR', LogisticRegression()))
models.append(('LDA', LinearDiscriminantAnalysis()))
models.append(('KNN', KNeighborsClassifier()))
models.append(('CART', DecisionTreeClassifier()))
models.append(('NB', GaussianNB()))
models.append(('SVM', SVC()))
# evaluate each model in turn
results = []
names = []
for name, model in models:
    kfold = model_selection.KFold(n_splits=12, random_state=seed)
    cv_results = model_selection.cross_val_score(model, X_train, Y_train, cv=kfold, scoring=scoring)
    results.append(cv_results)
    names.append(name)
    msg = "%s: %f (%f)" % (name, cv_results.mean(), cv_results.std())
    print(msg)

and here is the error I get:

ValueError                                Traceback (most recent call last)
<ipython-input-119-86bed78dded1> in <module>()
     12 for name, model in models:
     13         kfold = model_selection.KFold(n_splits=12, random_state=seed)
---> 14         cv_results = model_selection.cross_val_score(model, X_train, Y_train, cv=kfold, scoring=scoring)
     15         results.append(cv_results)
     16         names.append(name)

C:\ProgramData\Anaconda3\lib\site-packages\sklearn\model_selection\_validation.py in cross_val_score(estimator, X, y, groups, scoring, cv, n_jobs, verbose, fit_params, pre_dispatch)
    138                                               train, test, verbose, None,
    139                                               fit_params)
--> 140                       for train, test in cv_iter)
    141     return np.array(scores)[:, 0]
    142 

C:\ProgramData\Anaconda3\lib\site-packages\sklearn\externals\joblib\parallel.py in __call__(self, iterable)
    756             # was dispatched. In particular this covers the edge
    757             # case of Parallel used with an exhausted iterator.
--> 758             while self.dispatch_one_batch(iterator):
    759                 self._iterating = True
    760             else:

C:\ProgramData\Anaconda3\lib\site-packages\sklearn\externals\joblib\parallel.py in dispatch_one_batch(self, iterator)
    606                 return False
    607             else:
--> 608                 self._dispatch(tasks)
    609                 return True
    610 

C:\ProgramData\Anaconda3\lib\site-packages\sklearn\externals\joblib\parallel.py in _dispatch(self, batch)
    569         dispatch_timestamp = time.time()
    570         cb = BatchCompletionCallBack(dispatch_timestamp, len(batch), self)
--> 571         job = self._backend.apply_async(batch, callback=cb)
    572         self._jobs.append(job)
    573 

C:\ProgramData\Anaconda3\lib\site-packages\sklearn\externals\joblib\_parallel_backends.py in apply_async(self, func, callback)
    107     def apply_async(self, func, callback=None):
    108         """Schedule a func to be run"""
--> 109         result = ImmediateResult(func)
    110         if callback:
    111             callback(result)

C:\ProgramData\Anaconda3\lib\site-packages\sklearn\externals\joblib\_parallel_backends.py in __init__(self, batch)
    324         # Don't delay the application, to avoid keeping the input
    325         # arguments in memory
--> 326         self.results = batch()
    327 
    328     def get(self):

C:\ProgramData\Anaconda3\lib\site-packages\sklearn\externals\joblib\parallel.py in __call__(self)
    129 
    130     def __call__(self):
--> 131         return [func(*args, **kwargs) for func, args, kwargs in self.items]
    132 
    133     def __len__(self):

C:\ProgramData\Anaconda3\lib\site-packages\sklearn\externals\joblib\parallel.py in <listcomp>(.0)
    129 
    130     def __call__(self):
--> 131         return [func(*args, **kwargs) for func, args, kwargs in self.items]
    132 
    133     def __len__(self):

C:\ProgramData\Anaconda3\lib\site-packages\sklearn\model_selection\_validation.py in _fit_and_score(estimator, X, y, scorer, train, test, verbose, parameters, fit_params, return_train_score, return_parameters, return_n_test_samples, return_times, error_score)
    236             estimator.fit(X_train, **fit_params)
    237         else:
--> 238             estimator.fit(X_train, y_train, **fit_params)
    239 
    240     except Exception as e:

C:\ProgramData\Anaconda3\lib\site-packages\sklearn\linear_model\logistic.py in fit(self, X, y, sample_weight)
   1171 
   1172         X, y = check_X_y(X, y, accept_sparse='csr', dtype=np.float64,
-> 1173                          order="C")
   1174         check_classification_targets(y)
   1175         self.classes_ = np.unique(y)

C:\ProgramData\Anaconda3\lib\site-packages\sklearn\utils\validation.py in check_X_y(X, y, accept_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, multi_output, ensure_min_samples, ensure_min_features, y_numeric, warn_on_dtype, estimator)
    519     X = check_array(X, accept_sparse, dtype, order, copy, force_all_finite,
    520                     ensure_2d, allow_nd, ensure_min_samples,
--> 521                     ensure_min_features, warn_on_dtype, estimator)
    522     if multi_output:
    523         y = check_array(y, 'csr', force_all_finite=True, ensure_2d=False,

C:\ProgramData\Anaconda3\lib\site-packages\sklearn\utils\validation.py in check_array(array, accept_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, warn_on_dtype, estimator)
    380                                       force_all_finite)
    381     else:
--> 382         array = np.array(array, dtype=dtype, order=order, copy=copy)
    383 
    384         if ensure_2d:

ValueError: could not convert string to float: 'Jon'

I really want to use a Naive-Bayes model since a lot of my features are text, but I can't even get past this error :(

I am trying to build a model to predict if a sale will win or lose based off these features.

Upvotes: 0

Views: 653

Answers (1)

zimmerrol
zimmerrol

Reputation: 4951

You are trying to apply ML technique on a feature vector which consists out of strings. This is not possible, as the mathmatical operations are only defined for double/float values. To solve this error, you have to convert this string labels into numerical representations. To do this, you can use the sklearn.preprocessing.LabelEncoder. 

>>> le = preprocessing.LabelEncoder()
>>> le.fit(["paris", "paris", "tokyo", "amsterdam"])
LabelEncoder()
>>> list(le.classes_)
['amsterdam', 'paris', 'tokyo']
>>> le.transform(["tokyo", "tokyo", "paris"]) 
array([2, 2, 1]...)
>>> list(le.inverse_transform([2, 2, 1]))
['tokyo', 'tokyo', 'paris']

You can find more information in the documentation.

Upvotes: 2

Related Questions