feat/extend-math-words-list (#1)

- add math words (3d375979e88b67480884a1e52da5873b4313b36b)

handler.py

@@ -378,8 +378,8 @@ def load_math_terms():
     math_terms_dict = {}
     for term in MATH_WORDS:
         if term in MATH_PREFIXES:
-            math_terms_dict[f"(^|[^a-zA-Z]){term}(s|es)?([^a-zA-Z]|$)"] = term
-            math_terms.append(f"(^|[^a-zA-Z]){term}(s|es)?([^a-zA-Z]|$)")
+            math_terms_dict[f"(^|[^a-zA-Z]){term}(s|es|d|ed)?([^a-zA-Z]|$)"] = term
+            math_terms.append(f"(^|[^a-zA-Z]){term}(s|es|d|ed)?([^a-zA-Z]|$)")
         else:
             math_terms.append(term)
             math_terms_dict[term] = term

requirements.txt

@@ -1,7 +1,7 @@
 clean-text==0.6.0
 num2words==0.5.10
-numpy==1.22.4
-scipy==1.7.3
-torch==1.11.0
-transformers==4.36.0
-nltk==3.8.0
+numpy==1.24.4
+scipy==1.9.2
+torch==2.3.1
+transformers==4.46.1
+nltk==3.9.1

utils.py

@@ -295,6 +295,427 @@ MATH_WORDS = [
     "unit rate",
     "variability",
     "variable",
+    "abundant number",
+    "accurate",
+    "acre",
+    "addition fact",
+    "algebraic",
+    "altitude",
+    "apex",
+    "arithmetic facts",
+    "associative property",
+    "astronomical unit",
+    "base",
+    "baseline",
+    "billion",
+    "celsius",
+    "census",
+    "cent",
+    "center of a circle",
+    "center of a sphere",
+    "chance",
+    "circle graph",
+    "column",
+    "combine",
+    "common fraction",
+    "comparison diagram",
+    "comparison story",
+    "compass",
+    "complement",
+    "concave polygon",
+    "concentric circles",
+    "consecutive",
+    "constant",
+    "continuous model of area",
+    "continuous model of volume",
+    "contour",
+    "conversion fact",
+    "convex polygon",
+    "counting numbers",
+    "counting up subtraction",
+    "cover-up method",
+    "cross multiplication",
+    "cubic",
+    "cubit",
+    "curved surface",
+    "cylinder",
+    "decagon",
+    "decimeter",
+    "deficient number",
+    "density",
+    "discrete model",
+    "displacement method",
+    "divisibility test",
+    "divisible by",
+    "dodecahedron",
+    "double stem plot",
+    "doubles fact",
+    "egyptian multiplication",
+    "elevation",
+    "embed figure",
+    "end point",
+    "enlarge",
+    "equal",
+    "equal groups",
+    "equal parts",
+    "equidistant marks",
+    "equilateral polygon",
+    "equivalent fractions",
+    "european subtraction",
+    "expanded notation",
+    "expected outcome",
+    "exponential",
+    "extended facts",
+    "fact power",
+    "fact triangle",
+    "factor",
+    "factors of numbers",
+    "fahrenheit",
+    "false number sentence",
+    "figurate numbers",
+    "flowchart",
+    "fluid ounce",
+    "fractional part",
+    "fulcrum",
+    "function machine",
+    "furlong",
+    "genus",
+    "geoboard",
+    "geometric solid",
+    "geometry template",
+    "girth",
+    "golden ratio",
+    "golden rectangle",
+    "graph key",
+    "grouping symbol",
+    "hemisphere",
+    "icosahedron",
+    "improper fraction",
+    "inch",
+    "index of locations",
+    "indirect measurement",
+    "input",
+    "inscribed polygon",
+    "instance of a pattern",
+    "interior of a figure",
+    "interpolate",
+    "irrational",
+    "isometry transformation",
+    "isosceles trapezoid",
+    "juxtapose",
+    "key sequence",
+    "label",
+    "landmark",
+    "latitude",
+    "lattice multiplication",
+    "left to right subtraction",
+    "leg of a right triangle",
+    "like terms",
+    "line graph",
+    "line of reflection",
+    "line of symmetry",
+    "line symmetry",
+    "lines of latitude",
+    "lines of longitude",
+    "longitude",
+    "magnitude estimate",
+    "map legend",
+    "map scale",
+    "maximum",
+    "measurement division",
+    "measurement unit",
+    "meridian bar",
+    "metric system",
+    "midpoint",
+    "mile",
+    "millisecond",
+    "minimum",
+    "minuend",
+    "mirror image",
+    "mobius",
+    "modal",
+    "multiplication counting principle",
+    "multiplication diagram",
+    "multiplication fact",
+    "multiplication symbols",
+    "multiplication use class",
+    "negative rational numbers",
+    "nested parentheses",
+    "net score",
+    "net weight",
+    "nonagon",
+    "nonconvex polygon",
+    "normal span",
+    "number grid",
+    "number sequence",
+    "numeral",
+    "numeration",
+    "octahedron",
+    "open proportion",
+    "operation",
+    "operation symbol",
+    "opposite angle",
+    "opposite change rule",
+    "opposite of a number",
+    "opposite side",
+    "order of magnitude",
+    "order of operations",
+    "order of rotation symmetry",
+    "ordinal number",
+    "pan balance",
+    "parabola",
+    "parallel lines",
+    "parallel planes",
+    "part to part ratio",
+    "part to whole ratio",
+    "part whole fraction",
+    "partial differences subtraction",
+    "partial products multiplication",
+    "partial quotients division",
+    "partial sums addition",
+    "partitive division",
+    "parts and total diagram",
+    "per capita",
+    "per unit rate",
+    "percent circle",
+    "perfect number",
+    "perpetual calendar",
+    "pie graph",
+    "plane",
+    "plane figure",
+    "point symmetry",
+    "population density",
+    "precise",
+    "predict",
+    "prediction line",
+    "preimage",
+    "prime factorization",
+    "prime meridian",
+    "probability",
+    "probability meter",
+    "probability tree diagram",
+    "proper factor",
+    "proper fraction",
+    "property",
+    "quadrangle",
+    "quick common denominator",
+    "quotitive division",
+    "random draw",
+    "random experiment",
+    "random number",
+    "random sample",
+    "rank",
+    "rate diagram",
+    "rate multiplication ",
+    "rate unit",
+    "recall survey",
+    "rectangular array",
+    "rectangular coordinate grid",
+    "rectangular prism",
+    "rectangular pyramid",
+    "rectilinear figure",
+    "reflection",
+    "reflex angle",
+    "regular polyhedron",
+    "regular tessellation",
+    "relation symbol",
+    "revolution",
+    "right cone",
+    "right cylinder",
+    "right prism",
+    "right pyramid",
+    "right triangle",
+    "roman numerals",
+    "rotation symmetry",
+    "same change rule for subtraction",
+    "scale model",
+    "scale of a map",
+    "scale of a number line",
+    "sector",
+    "segment",
+    "sequence",
+    "significant digits",
+    "similar figures",
+    "simpler form",
+    "situtation diagram",
+    "skew lines",
+    "slanted",
+    "slide rule",
+    "span",
+    "stacked bar graph",
+    "standard unit",
+    "stem and leaf plot",
+    "step graph",
+    "straightedge",
+    "substitute",
+    "subtrahend",
+    "surface",
+    "symmetric",
+    "tally",
+    "tangent",
+    "tangent circles",
+    "temperature",
+    "template",
+    "tetrahedron",
+    "theorem",
+    "tile",
+    "tiling",
+    "time graph",
+    "timeline",
+    "top heavy fraction",
+    "topological",
+    "topology",
+    "trade first subtraction",
+    "tree diagram",
+    "triangular",
+    "true number sentence",
+    "truncate",
+    "twin primes",
+    "unlike denominators",
+    "unlike fractions",
+    "vanishing ",
+    "venn diagram",
+    "vernal equinox",
+    "weight",
+    "width",
+    "base of a prism",
+    "base of a pyramid",
+    "face",
+    "numerical data",
+    "opposite",
+    "pace",
+    "per",
+    "region",
+    "sign",
+    "alternate interior angles",
+    "base of an exponent",
+    "cone",
+    "congruent",
+    "counterclockwise",
+    "cube root",
+    "hypotenuse",
+    "irrational number",
+    "linear relationship",
+    "positive association",
+    "rate of change",
+    "translation",
+    "transversal",
+    "circumference",
+    "corresponding",
+    "expand",
+    "population",
+    "proportion",
+    "radius",
+    "random",
+    "repeating decimal",
+    "representative",
+    "scaled",
+    "withdrawal",
+    "center",
+    "edge",
+    "height of a parallelogram or triangle",
+    "net",
+    "speed",
+    "table",
+    "term",
+    "adjacent",
+    "complementary",
+    "cross-section",
+    "cross section",
+    "deposit",
+    "event",
+    "measurement error",
+    "proportional",
+    "simulation",
+    "center of a dilation",
+    "clockwise",
+    "dilation",
+    "function",
+    "negative association",
+    "pythagorean theorem",
+    "relative frequency",
+    "rigid transformation",
+    "scale factor",
+    "scatter plot",
+    "similar",
+    "sphere",
+    "two-way table",
+    "additive identity",
+    "additive inverse",
+    "box and whisker plot",
+    "cartesian coordinates",
+    "central angle",
+    "chord",
+    "combination",
+    "commutative property",
+    "coplanar",
+    "cross product",
+    "dependent events",
+    "difference",
+    "dividend",
+    "equilateral triangle",
+    "error of measurement",
+    "factorial",
+    "formula",
+    "identity property of",
+    "independent events",
+    "infinity",
+    "inscribed angle",
+    "intercept",
+    "intercepted arc",
+    "inverse",
+    "inverse operations",
+    "isosceles triangle",
+    "least common denominator",
+    "like fractions",
+    "locus",
+    "logic",
+    "lowest terms",
+    "mode",
+    "multiplicative identity",
+    "multiplicative inverse",
+    "mutually exclusive events",
+    "natural numbers",
+    "normal",
+    "permutation",
+    "pi",
+    "point",
+    "power",
+    "range",
+    "rate",
+    "ray",
+    "real numbers",
+    "rectangular",
+    "root",
+    "rotation",
+    "scalene triangle",
+    "scattergram",
+    "set",
+    "statistics",
+    "terminating decimal",
+    "transformation",
+    "x intercept",
+    "x-axis",
+    "x-intercept",
+    "y intercept",
+    "y-axis",
+    "y-intercept",
+    "zero",
+    "zero property of multiplication",
+    "base of a parallelogram",
+    "base of a triangle",
+    "height",
+    "chance experiment",
+    "diameter",
+    "mean",
+    "percentage",
+    "sample",
+    "legs",
+    "outlier",
+    "slope",
+    "square root",
+    "system of equations",
+    "tessellation",
 ]
 
 def get_num_words(text):