if not (isinstance(_arg1[0], str)):
raise TypeError
supportedLibraries = {"nltk", "textblob"}
library = library.lower()
if library not in supportedLibraries:
raise ValueError
scores = []
if library == "nltk":
sid = SentimentIntensityAnalyzer()
for text in _arg1:
sentimentResults = sid.polarity_scores(text)
score = sentimentResults["compound"]
scores.append(score)
elif library == "textblob":
for text in _arg1:
currScore = TextBlob(text)
scores.append(currScore.sentiment.polarity)
return scores
if __name__ == "__main__":
setup_utils.deploy_model(
"Sentiment Analysis",
SentimentAnalysis,
"Returns a sentiment score between -1 and 1 for "
"a given string",
)
'''
# one sample test with mean
if len(_arg2) == 1:
test_stat, p_value = stats.ttest_1samp(_arg1, _arg2)
return p_value
# two sample t-test where _arg1 is numeric and _arg2 is a binary factor
elif len(set(_arg2)) == 2:
# each sample in _arg1 needs to have a corresponding classification
# in _arg2
if not (len(_arg1) == len(_arg2)):
raise ValueError
class1, class2 = set(_arg2)
sample1 = []
sample2 = []
for i in range(len(_arg1)):
if _arg2[i] == class1:
sample1.append(_arg1[i])
else:
sample2.append(_arg1[i])
test_stat, p_value = stats.ttest_ind(sample1, sample2, equal_var=False)
return p_value
# arg1 is a sample and arg2 is a sample
else:
test_stat, p_value = stats.ttest_ind(_arg1, _arg2, equal_var=False)
return p_value
if __name__ == '__main__':
setup_utils.deploy_model('ttest', ttest,
'Returns the p-value form a t-test')
'25 unique values')
raise ValueError
integerEncoded = labelEncoder.fit_transform(array(col))
integerEncoded = integerEncoded.reshape(len(col), 1)
oneHotEncoded = oneHotEncoder.fit_transform(integerEncoded)
transformedMatrix = oneHotEncoded.transpose()
encodedCols += list(transformedMatrix)
dataDict = {}
for i in range(len(encodedCols)):
dataDict[f'col{1 + i}'] = list(encodedCols[i])
if component <= 0 or component > len(dataDict):
print('ERROR: Component specified must be >= 0 and '
'<= number of arguments')
raise ValueError
df = pd.DataFrame(data=dataDict, dtype=float)
scale = StandardScaler()
scaledData = scale.fit_transform(df)
pca = sklearnPCA()
pcaComponents = pca.fit_transform(scaledData)
return pcaComponents[:, component - 1].tolist()
if __name__ == '__main__':
setup_utils.deploy_model('PCA', PCA,
'Returns the specified principal component')
import scipy.stats as stats
from tabpy.models.utils import setup_utils
def anova(_arg1, _arg2, *_argN):
"""
ANOVA is a statistical hypothesis test that is used to compare
two or more group means for equality.For more information on
the function and how to use it please refer to tabpy-tools.md
"""
cols = [_arg1, _arg2] + list(_argN)
for col in cols:
if not isinstance(col[0], (int, float)):
print("values must be numeric")
raise ValueError
_, p_value = stats.f_oneway(_arg1, _arg2, *_argN)
return p_value
if __name__ == "__main__":
setup_utils.deploy_model("anova", anova,
"Returns the p-value form an ANOVA test")
"""
# one sample test with mean
if len(_arg2) == 1:
test_stat, p_value = stats.ttest_1samp(_arg1, _arg2)
return p_value
# two sample t-test where _arg1 is numeric and _arg2 is a binary factor
elif len(set(_arg2)) == 2:
# each sample in _arg1 needs to have a corresponding classification
# in _arg2
if not (len(_arg1) == len(_arg2)):
raise ValueError
class1, class2 = set(_arg2)
sample1 = []
sample2 = []
for i in range(len(_arg1)):
if _arg2[i] == class1:
sample1.append(_arg1[i])
else:
sample2.append(_arg1[i])
test_stat, p_value = stats.ttest_ind(sample1, sample2, equal_var=False)
return p_value
# arg1 is a sample and arg2 is a sample
else:
test_stat, p_value = stats.ttest_ind(_arg1, _arg2, equal_var=False)
return p_value
if __name__ == "__main__":
setup_utils.deploy_model("ttest", ttest,
"Returns the p-value form a t-test")
import scipy.stats as stats
from tabpy.models.utils import setup_utils
def anova(_arg1, _arg2, *_argN):
'''
ANOVA is a statistical hypothesis test that is used to compare
two or more group means for equality.For more information on
the function and how to use it please refer to tabpy-tools.md
'''
cols = [_arg1, _arg2] + list(_argN)
for col in cols:
if not isinstance(col[0], (int, float)):
print("values must be numeric")
raise ValueError
_, p_value = stats.f_oneway(_arg1, _arg2, *_argN)
return p_value
if __name__ == '__main__':
setup_utils.deploy_model(
'anova',
anova,
'Returns the p-value form an ANOVA test')
tabpy-tools.md
'''
if not (isinstance(_arg1[0], str)):
raise TypeError
supportedLibraries = {'nltk', 'textblob'}
library = library.lower()
if library not in supportedLibraries:
raise ValueError
scores = []
if library == 'nltk':
sid = SentimentIntensityAnalyzer()
for text in _arg1:
sentimentResults = sid.polarity_scores(text)
score = sentimentResults['compound']
scores.append(score)
elif library == 'textblob':
for text in _arg1:
currScore = TextBlob(text)
scores.append(currScore.sentiment.polarity)
return scores
if __name__ == '__main__':
setup_utils.deploy_model(
'Sentiment Analysis', SentimentAnalysis,
'Returns a sentiment score between -1 and 1 for '
'a given string')
"25 unique values")
raise ValueError
integerEncoded = labelEncoder.fit_transform(array(col))
integerEncoded = integerEncoded.reshape(len(col), 1)
oneHotEncoded = oneHotEncoder.fit_transform(integerEncoded)
transformedMatrix = oneHotEncoded.transpose()
encodedCols += list(transformedMatrix)
dataDict = {}
for i in range(len(encodedCols)):
dataDict[f"col{1 + i}"] = list(encodedCols[i])
if component <= 0 or component > len(dataDict):
print("ERROR: Component specified must be >= 0 and "
"<= number of arguments")
raise ValueError
df = pd.DataFrame(data=dataDict, dtype=float)
scale = StandardScaler()
scaledData = scale.fit_transform(df)
pca = sklearnPCA()
pcaComponents = pca.fit_transform(scaledData)
return pcaComponents[:, component - 1].tolist()
if __name__ == "__main__":
setup_utils.deploy_model("PCA", PCA,
"Returns the specified principal component")