silly-penguin/validation.py at main · advanced-computing/silly-penguin · 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
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
"""Pandera validation schemas for all data sources."""

from __future__ import annotations

import pandera as pa
from pandera import Check, Column, DataFrameSchema

# ----------------------------
# Constants
# ----------------------------
VALID_DEMAND_TYPES = {"Demand", "Day-ahead demand forecast"}

TEMP_MIN_C = -50.0
TEMP_MAX_C = 60.0

DEMAND_MIN = 0.0
DEMAND_MAX = 500_000.0  # higher bound for large BAs like PJM/MISO

INTERCHANGE_MIN = -200_000.0
INTERCHANGE_MAX = 200_000.0

GENERATION_MIN = 0.0
GENERATION_MAX = 500_000.0

NG_PRICE_MIN = 0.0
NG_PRICE_MAX = 50.0  # $/MMBtu — extreme but possible

AVG_TEMP_TOL = 0.2


# ----------------------------
# 1) EIA Demand Schema
# ----------------------------
demand_schema = DataFrameSchema(
    {
        "period": Column(pa.DateTime, nullable=False),
        "type-name": Column(
            pa.String,
            nullable=False,
            checks=Check.isin(VALID_DEMAND_TYPES),
        ),
        "value": Column(
            pa.Float,
            nullable=False,
            checks=[Check.ge(DEMAND_MIN), Check.le(DEMAND_MAX)],
        ),
        "respondent": Column(pa.String, nullable=False),
    },
    strict=False,
)


# ----------------------------
# 2) EIA Interchange Schema
# ----------------------------
interchange_schema = DataFrameSchema(
    {
        "period": Column(pa.DateTime, nullable=False),
        "value": Column(
            pa.Float,
            nullable=False,
            checks=[Check.ge(INTERCHANGE_MIN), Check.le(INTERCHANGE_MAX)],
        ),
        "fromba": Column(pa.String, nullable=False),
        "toba": Column(pa.String, nullable=False),
    },
    strict=False,
)


# ----------------------------
# 3) EIA Fuel Type Schema
# ----------------------------
fuel_type_schema = DataFrameSchema(
    {
        "period": Column(pa.DateTime, nullable=False),
        "value": Column(
            pa.Float,
            nullable=False,
            checks=[Check.ge(GENERATION_MIN), Check.le(GENERATION_MAX)],
        ),
        "respondent": Column(pa.String, nullable=False),
        "fueltype": Column(pa.String, nullable=False),
    },
    strict=False,
)


# ----------------------------
# 4) Natural Gas Price Schema
# ----------------------------
ng_price_schema = DataFrameSchema(
    {
        "date": Column(pa.DateTime, nullable=False),
        "ng_price": Column(
            pa.Float,
            nullable=False,
            checks=[Check.ge(NG_PRICE_MIN), Check.le(NG_PRICE_MAX)],
        ),
    },
    strict=False,
)


# ----------------------------
# 5) Weather Schema
# ----------------------------
weather_schema = DataFrameSchema(
    {
        "date": Column(pa.DateTime, nullable=False),
        "max_temp": Column(pa.Float, nullable=False, checks=Check.between(TEMP_MIN_C, TEMP_MAX_C)),
        "min_temp": Column(pa.Float, nullable=False, checks=Check.between(TEMP_MIN_C, TEMP_MAX_C)),
        "avg_temp": Column(pa.Float, nullable=False, checks=Check.between(TEMP_MIN_C, TEMP_MAX_C)),
        "ba": Column(pa.String, nullable=False),
    },
    strict=False,
    checks=[
        Check(
            lambda df: (df["max_temp"] >= df["min_temp"]).all(),
            error="max_temp < min_temp found.",
        ),
    ],
)


# ----------------------------
# 6) Merged Daily Schema
# ----------------------------
merged_schema = DataFrameSchema(
    {
        "date": Column(pa.DateTime, nullable=False),
        "avg_demand_mwh": Column(
            pa.Float,
            nullable=False,
            checks=[Check.ge(DEMAND_MIN), Check.le(DEMAND_MAX)],
        ),
        "avg_temp": Column(
            pa.Float,
            nullable=False,
            checks=Check.between(TEMP_MIN_C, TEMP_MAX_C),
        ),
    },
    strict=False,
)


# ----------------------------
# Convenience helpers
# ----------------------------
def validate_demand(df):
    """Validate raw EIA demand dataframe."""
    return demand_schema.validate(df)


def validate_interchange(df):
    """Validate raw EIA interchange dataframe."""
    return interchange_schema.validate(df)


def validate_fuel_type(df):
    """Validate raw EIA fuel type dataframe."""
    return fuel_type_schema.validate(df)


def validate_ng_price(df):
    """Validate natural gas price dataframe."""
    return ng_price_schema.validate(df)


def validate_weather(df):
    """Validate raw weather dataframe."""
    return weather_schema.validate(df)


def validate_merged(df):
    """Validate merged dataframe."""
    return merged_schema.validate(df)