monte-carlo-app/app_utility.py at main · TheOpenScienceNerd/monte-carlo-app · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
"""Basic utility functions for loading and formatting data in the app.
"""
import pandas as pd

def remove_daytype_formatting(df):
    """
    Standardizes day type DataFrame for internal use.

    Removes formatting (e.g., emojis) from column names and values
    used for display in the Streamlit app, converting them to a
    standard format required by the simulation engine.

    Parameters
    ----------
    df : pd.DataFrame
        DataFrame containing day type probabilities, potentially with
        display formatting. Expected columns include 'Type of sales day'
        and potentially others depending on the display format.

    Returns
    -------
    pd.DataFrame
        DataFrame with standardized column names ('day_type') and values
        ('good', 'fair', 'poor').
    """
    column_names = {"Type of sales day": "day_type"}
    day_recodings = {
        "day_type": {"☀️ Good": "good", "⛅ Fair": "fair", "⛈️ Poor": "poor"}
    }
    return df.rename(columns=column_names).replace(day_recodings)


def remove_demand_formatting(df):
    """
    Standardizes demand DataFrame for internal use.

    Removes formatting (e.g., emojis) from column names used for display
    in the Streamlit app, converting them to a standard format required
    by the simulation engine.

    Parameters
    ----------
    df : pd.DataFrame
        DataFrame containing demand probabilities for different day types,
        potentially with display formatting in column names. Expected columns
        include '📰 Demand', '☀️ Good', '⛅ Fair', '⛈️ Poor'.

    Returns
    -------
    pd.DataFrame
        DataFrame with standardized column names ('demand', 'good', 'fair',
        'poor').
    """
    column_names = {
        "📰 Demand": "demand",
        "☀️ Good": "good",
        "⛅ Fair": "fair",
        "⛈️ Poor": "poor",
    }
    return df.rename(columns=column_names)


def fetch_demand(path):
    """
    Fetches and formats demand probability data from a CSV file.

    Reads the demand distribution data from the specified path,
    renames columns for user-friendly display in Streamlit (e.g., adding
    emojis), and caches the result to improve performance.

    Parameters
    ----------
    path : str or Path-like
        The file path to the CSV containing demand probability data.
        The CSV should have columns like 'demand', 'good', 'fair', 'poor'.

    Returns
    -------
    pd.DataFrame
        DataFrame containing the demand data with columns formatted for display
        ('📰 Demand', '☀️ Good', '⛅ Fair', '⛈️ Poor').
    """
    # Fetch basic data frame containing input data
    column_names = {
        "demand": "📰 Demand",
        "good": "☀️ Good",
        "fair": "⛅ Fair",
        "poor": "⛈️ Poor",
    }
    return pd.read_csv(path).rename(columns=column_names)


def fetch_day_type(path):
    """
    Fetches and formats day type probability data from a CSV file.

    Reads the day type probability data from the specified path,
    recodes values and renames columns for user-friendly display in
    Streamlit (e.g., adding emojis), and caches the result to improve
    performance.

    Parameters
    ----------
    path : str or Path-like
        The file path to the CSV containing day type probability data.
        The CSV should have columns like 'day_type' and 'prob', with
        'day_type' values such as 'good', 'fair', 'poor'.

    Returns
    -------
    pd.DataFrame
        DataFrame containing the day type data with values and columns
        formatted for display ('Type of sales day', emojis for day types).
    """
    # Fetch basic data frame containing input data
    column_names = {"day_type": "Type of sales day"}
    day_recodings = {
        "day_type": {"good": "☀️ Good", "fair": "⛅ Fair", "poor": "⛈️ Poor"}
    }
    df = pd.read_csv(path).replace(day_recodings).rename(columns=column_names)
    return df