Beispiel #1
0
    def getFreAndWeight(self):
        try:
            doc = self.documentEdit.text()
            term = self.termEdit.text()

            freq = inverted_index.frequence(term, doc + ".txt")
            weight = inverted_index.weight(term, doc + ".txt")
            self.freqLabel.setText('Frequence ' + str(freq))
            self.weightLabel.setText('Weight %.2f' % weight)
        except FileNotFoundError:
            self.popup("No document found",
                       "There is no document in the collectin with that name",
                       "No document Found")
Beispiel #2
0
def cosinus_measure(query, doc_name):
    """
    Return Cosinus measure between a document and a query
    :param query:The query string
    :type: str
    :param doc_name: the document name
    :type: str
    :return: inner product
    :type: float
    """
    x_values = [1 for term in query]
    y_values = [
        pow(inverted_index.weight(term, doc_name), 2) for term in query
    ]
    x_sum = sum(x_values)
    y_sum = sum(y_values)
    measure = inner_product(query, doc_name) / math.sqrt(x_sum * y_sum)
    return measure
Beispiel #3
0
def inner_product(query, doc_name):
    """
    Return the inner product between a document and a query
    :param query:The query string
    :type: str
    :param doc_name: the document name
    :type: str
    :return: inner product
    :type: float
    """

    sum_ = 0
    for term in query:
        x = 1
        y = inverted_index.weight(term, doc_name)
        sum_ += x * y

    return sum_
Beispiel #4
0
def dice_coefficient(query, doc_name):
    """
    Return Dice coefficient between a document and a query
    :param query:The query string
    :type: str
    :param doc_name: the document name
    :type: str
    :return: inner product
    :type: float
    """
    x_values = [1 for term in query]
    y_values = [
        pow(inverted_index.weight(term, doc_name), 2) for term in query
    ]
    x_sum = sum(x_values)
    y_sum = sum(y_values)
    coeff = (2 * inner_product(query, doc_name)) / x_sum + y_sum
    return coeff
Beispiel #5
0
def jackard_measure(query, doc_name):
    """
    Return jackard measure between a document and a query
    :param query:The query string
    :type: str
    :param doc_name: the document name
    :type: str
    :return: inner product
    :type: float
    """
    x_values = [1 for term in query]
    y_values = [
        pow(inverted_index.weight(term, doc_name), 2) for term in query
    ]
    x_sum = sum(x_values)
    y_sum = sum(y_values)
    measure = inner_product(
        query, doc_name) / (x_sum + y_sum - inner_product(query, doc_name))
    return measure