Formula

There are two primary goals for this Formula class.

Parse and normalize a single formula
Count, order, filter a list of formulas

Import

[1]:

from bobleesj.utils.parsers.formula import Formula

Formula

Parse

[2]:

formula = Formula("NdSi2")
print("Parsed formula:", formula.parsed_formula)
print("Elements:", formula.elements)
print("Indices:", formula.indices)
print("Element count:", formula.element_count)
print("Max, Min, Avg of indices:", formula.max_min_avg_index)

Parsed formula: [('Nd', 1.0), ('Si', 2.0)]
Elements: ['Nd', 'Si']
Indices: [1.0, 2.0]
Element count: 2
Max, Min, Avg of indices: (2.0, 1.0, 1.5)

Normalize formula

[3]:

# Normalized index values, default is 6 decimal places
print("Indices:", formula.get_normalized_indices())
print("Formula:", formula.get_normalized_formula())
print("Parsed formula:", formula.get_normalized_parsed_formula())

Indices: [0.333333, 0.666667]
Formula: Nd0.333333Si0.666667
Parsed formula: [('Nd', 0.333333), ('Si', 0.666667)]

[4]:

# Round to 3 decimal places
print("Indices:", formula.get_normalized_indices(decimals=3))
print("Formula:", formula.get_normalized_formula(decimals=3))
print("Parsed formula:", formula.get_normalized_parsed_formula(decimals=3))

Indices: [0.333, 0.667]
Formula: Nd0.333Si0.667
Parsed formula: [('Nd', 0.333), ('Si', 0.667)]

Sort formulas into composition type unary, binary, ternary, etc.

Count, order, filter a list of formulas

Count

[5]:

# Count all formulas in a list
Formula.count(["Cu", "NdSi2", "ThOs", "NdSi2Th2", "YNdThSi2"])

[5]:

[6]:

# Count the number of unique formulas
Formula.count_unique(["CuNdSi2", "CuNdSi2", "YNdThSi2"])

[6]:

[7]:

# Count the number of occurrences of each unique formula
Formula.count_individual(["NdSi2", "NdSi2", "YNdThSi2"])

[7]:

{'NdSi2': 2, 'YNdThSi2': 1}

[8]:

# Count and display duplicate formulas only
Formula.count_duplicates(["NdSi2", "NdSi2", "NdSi2Th2", "NdSi2Th2", "ThOs"])

[8]:

{'NdSi2': 2, 'NdSi2Th2': 2}

[9]:

# Count the number of formula provided
Formula.count_by_formula(["NdSi2", "NdSi2", "NdSi2Th2", "NdSi2Th2", "ThOs"], "NdSi2")

[9]:

[10]:

# Count by formula
Formula.count_by_formula(["NdSi2", "NdSi2", "NdSi2Th2", "NdSi2Th2", "ThOs"], "NdSi2")

[10]:

[11]:

# Count by compposition
Formula.count_by_composition(["NdSi2", "NdSi2", "NdSi2Th2", "NdSi2Th2", "ThOs"])

[11]:

{2: 3, 3: 2}

[12]:

# Get unique elements only
Formula.get_unique_elements(["NdSi2", "NdSi2", "NdSi2Th2", "NdSi2Th2", "ThOs"])

[12]:

{'Nd', 'Os', 'Si', 'Th'}

[13]:

# Get unique formulas only
Formula.get_unique_formulas(["NdSi2", "NdSi2", "NdSi2Th2", "NdSi2Th2", "ThOs"])

[13]:

{'NdSi2', 'NdSi2Th2', 'ThOs'}

[14]:

# Get element counts (ignore Stoichiometry)
Formula.get_element_count(["NdSi2", "NdSi2", "NdSi2Th2", "NdSi2Th2", "ThOs"])

[14]:

{'Nd': 4, 'Si': 4, 'Th': 3, 'Os': 1}

Order

[15]:

# Order formulas A->Z
Formula.order_by_alphabetical(["AB2", "AB", "BC2D2", "BBC2"])

[15]:

['AB', 'AB2', 'BBC2', 'BC2D2']

[16]:

# Order formulas Z->A
Formula.order_by_alphabetical(["AB2", "AB", "BC2D2", "BBC2"], reverse=True)

[16]:

['BC2D2', 'BBC2', 'AB2', 'AB']

Filter

[17]:

# Filter a list of formula by composition
sorted_formulas = Formula.filter_by_composition(["Cu", "NdSi2", "ThOs", "NdSi2Th2", "YNdThSi2"])

[18]:

# Filter by composition (e.g., binary)
Formula.filter_by_single_composition(["NdSi2", "NdSi2", "NdSi2Th2", "NdSi2Th2", "ThOs"], 2)

[18]:

['NdSi2', 'NdSi2', 'ThOs']

[19]:

# Filter by elements containing
Formula.filter_by_elements_containing(["NdSi2", "NdSi2", "NdSi2Th2", "NdSi2Th2", "ThOs"], ["Nd", "Si"])

[19]:

['NdSi2', 'NdSi2', 'NdSi2Th2', 'NdSi2Th2']

[20]:

# Filter by elements matching
Formula.filter_by_elements_matching(["NdSi2", "NdSi", "NdSi2Th2", "NdSi2Th2", "ThOs"], ["Nd", "Si"])

[20]:

['NdSi2', 'NdSi']