|
1
|
|
|
""" |
|
2
|
|
|
Helpers: constants and functions for motorized individual travel |
|
3
|
|
|
""" |
|
4
|
|
|
|
|
5
|
|
|
from pathlib import Path |
|
6
|
|
|
import json |
|
7
|
|
|
|
|
8
|
|
|
import numpy as np |
|
9
|
|
|
import pandas as pd |
|
10
|
|
|
|
|
11
|
|
|
import egon.data.config |
|
12
|
|
|
|
|
13
|
|
|
TESTMODE_OFF = ( |
|
14
|
|
|
egon.data.config.settings()["egon-data"]["--dataset-boundary"] |
|
15
|
|
|
== "Everything" |
|
16
|
|
|
) |
|
17
|
|
|
WORKING_DIR = Path(".", "emobility") |
|
18
|
|
|
DATA_BUNDLE_DIR = Path( |
|
19
|
|
|
".", |
|
20
|
|
|
"data_bundle_egon_data", |
|
21
|
|
|
"emobility", |
|
22
|
|
|
) |
|
23
|
|
|
DATASET_CFG = egon.data.config.datasets()["emobility_mit"] |
|
24
|
|
|
COLUMNS_KBA = [ |
|
25
|
|
|
"reg_district", |
|
26
|
|
|
"total", |
|
27
|
|
|
"mini", |
|
28
|
|
|
"medium", |
|
29
|
|
|
"luxury", |
|
30
|
|
|
"unknown", |
|
31
|
|
|
] |
|
32
|
|
|
CONFIG_EV = { |
|
33
|
|
|
"bev_mini": { |
|
34
|
|
|
"column": "mini", |
|
35
|
|
|
"tech_share": "bev_mini_share", |
|
36
|
|
|
"share": "mini_share", |
|
37
|
|
|
"factor": "mini_factor", |
|
38
|
|
|
}, |
|
39
|
|
|
"bev_medium": { |
|
40
|
|
|
"column": "medium", |
|
41
|
|
|
"tech_share": "bev_medium_share", |
|
42
|
|
|
"share": "medium_share", |
|
43
|
|
|
"factor": "medium_factor", |
|
44
|
|
|
}, |
|
45
|
|
|
"bev_luxury": { |
|
46
|
|
|
"column": "luxury", |
|
47
|
|
|
"tech_share": "bev_luxury_share", |
|
48
|
|
|
"share": "luxury_share", |
|
49
|
|
|
"factor": "luxury_factor", |
|
50
|
|
|
}, |
|
51
|
|
|
"phev_mini": { |
|
52
|
|
|
"column": "mini", |
|
53
|
|
|
"tech_share": "phev_mini_share", |
|
54
|
|
|
"share": "mini_share", |
|
55
|
|
|
"factor": "mini_factor", |
|
56
|
|
|
}, |
|
57
|
|
|
"phev_medium": { |
|
58
|
|
|
"column": "medium", |
|
59
|
|
|
"tech_share": "phev_medium_share", |
|
60
|
|
|
"share": "medium_share", |
|
61
|
|
|
"factor": "medium_factor", |
|
62
|
|
|
}, |
|
63
|
|
|
"phev_luxury": { |
|
64
|
|
|
"column": "luxury", |
|
65
|
|
|
"tech_share": "phev_luxury_share", |
|
66
|
|
|
"share": "luxury_share", |
|
67
|
|
|
"factor": "luxury_factor", |
|
68
|
|
|
}, |
|
69
|
|
|
} |
|
70
|
|
|
TRIP_COLUMN_MAPPING = { |
|
71
|
|
|
"location": "location", |
|
72
|
|
|
"use_case": "use_case", |
|
73
|
|
|
"nominal_charging_capacity_kW": "charging_capacity_nominal", |
|
74
|
|
|
"grid_charging_capacity_kW": "charging_capacity_grid", |
|
75
|
|
|
"battery_charging_capacity_kW": "charging_capacity_battery", |
|
76
|
|
|
"soc_start": "soc_start", |
|
77
|
|
|
"soc_end": "soc_end", |
|
78
|
|
|
"chargingdemand_kWh": "charging_demand", |
|
79
|
|
|
"park_start_timesteps": "park_start", |
|
80
|
|
|
"park_end_timesteps": "park_end", |
|
81
|
|
|
"drive_start_timesteps": "drive_start", |
|
82
|
|
|
"drive_end_timesteps": "drive_end", |
|
83
|
|
|
"consumption_kWh": "consumption", |
|
84
|
|
|
} |
|
85
|
|
|
MVGD_MIN_COUNT = 3700 if TESTMODE_OFF else 150 |
|
86
|
|
|
|
|
87
|
|
|
|
|
88
|
|
|
def read_kba_data(): |
|
89
|
|
|
"""Read KBA data from CSV""" |
|
90
|
|
|
return pd.read_csv( |
|
91
|
|
|
WORKING_DIR |
|
92
|
|
|
/ egon.data.config.datasets()["emobility_mit"]["original_data"][ |
|
93
|
|
|
"sources" |
|
94
|
|
|
]["KBA"]["file_processed"] |
|
95
|
|
|
) |
|
96
|
|
|
|
|
97
|
|
|
|
|
98
|
|
|
def read_rs7_data(): |
|
99
|
|
|
"""Read RegioStaR7 data from CSV""" |
|
100
|
|
|
return pd.read_csv( |
|
101
|
|
|
WORKING_DIR |
|
102
|
|
|
/ egon.data.config.datasets()["emobility_mit"]["original_data"][ |
|
103
|
|
|
"sources" |
|
104
|
|
|
]["RS7"]["file_processed"] |
|
105
|
|
|
) |
|
106
|
|
|
|
|
107
|
|
|
|
|
108
|
|
|
def read_simbev_metadata_file(scenario_name, section): |
|
109
|
|
|
"""Read metadata of simBEV run |
|
110
|
|
|
|
|
111
|
|
|
Parameters |
|
112
|
|
|
---------- |
|
113
|
|
|
scenario_name : str |
|
114
|
|
|
Scenario name |
|
115
|
|
|
section : str |
|
116
|
|
|
Metadata section to be returned, one of |
|
117
|
|
|
* "tech_data" |
|
118
|
|
|
* "charge_prob_slow" |
|
119
|
|
|
* "charge_prob_fast" |
|
120
|
|
|
|
|
121
|
|
|
Returns |
|
122
|
|
|
------- |
|
123
|
|
|
pd.DataFrame |
|
124
|
|
|
Config data |
|
125
|
|
|
""" |
|
126
|
|
|
trips_cfg = DATASET_CFG["original_data"]["sources"]["trips"] |
|
127
|
|
|
meta_file = DATA_BUNDLE_DIR / Path( |
|
128
|
|
|
"mit_trip_data", |
|
129
|
|
|
trips_cfg[scenario_name]["file"].split(".")[0], |
|
130
|
|
|
trips_cfg[scenario_name]["file_metadata"], |
|
131
|
|
|
) |
|
132
|
|
|
with open(meta_file) as f: |
|
133
|
|
|
meta = json.loads(f.read()) |
|
134
|
|
|
return pd.DataFrame.from_dict(meta.get(section, dict()), orient="index") |
|
135
|
|
|
|
|
136
|
|
|
|
|
137
|
|
|
def reduce_mem_usage( |
|
138
|
|
|
df: pd.DataFrame, show_reduction: bool = False |
|
139
|
|
|
) -> pd.DataFrame: |
|
140
|
|
|
"""Function to automatically check if columns of a pandas DataFrame can |
|
141
|
|
|
be reduced to a smaller data type. Source: |
|
142
|
|
|
https://www.mikulskibartosz.name/how-to-reduce-memory-usage-in-pandas/ |
|
143
|
|
|
|
|
144
|
|
|
Parameters |
|
145
|
|
|
---------- |
|
146
|
|
|
df: pd.DataFrame |
|
147
|
|
|
DataFrame to reduce memory usage on |
|
148
|
|
|
show_reduction : bool |
|
149
|
|
|
If True, print amount of memory reduced |
|
150
|
|
|
|
|
151
|
|
|
Returns |
|
152
|
|
|
------- |
|
153
|
|
|
pd.DataFrame |
|
154
|
|
|
DataFrame with memory usage decreased |
|
155
|
|
|
""" |
|
156
|
|
|
start_mem = df.memory_usage().sum() / 1024 ** 2 |
|
157
|
|
|
|
|
158
|
|
|
for col in df.columns: |
|
159
|
|
|
col_type = df[col].dtype |
|
160
|
|
|
|
|
161
|
|
|
if col_type != object and str(col_type) != "category": |
|
162
|
|
|
c_min = df[col].min() |
|
163
|
|
|
c_max = df[col].max() |
|
164
|
|
|
|
|
165
|
|
|
if str(col_type)[:3] == "int": |
|
166
|
|
|
if ( |
|
167
|
|
|
c_min > np.iinfo(np.int16).min |
|
168
|
|
|
and c_max < np.iinfo(np.int16).max |
|
169
|
|
|
): |
|
170
|
|
|
df[col] = df[col].astype("int16") |
|
171
|
|
|
elif ( |
|
172
|
|
|
c_min > np.iinfo(np.int32).min |
|
173
|
|
|
and c_max < np.iinfo(np.int32).max |
|
174
|
|
|
): |
|
175
|
|
|
df[col] = df[col].astype("int32") |
|
176
|
|
|
else: |
|
177
|
|
|
df[col] = df[col].astype("int64") |
|
178
|
|
|
else: |
|
179
|
|
|
if ( |
|
180
|
|
|
c_min > np.finfo(np.float32).min |
|
181
|
|
|
and c_max < np.finfo(np.float32).max |
|
182
|
|
|
): |
|
183
|
|
|
df[col] = df[col].astype("float32") |
|
184
|
|
|
else: |
|
185
|
|
|
df[col] = df[col].astype("float64") |
|
186
|
|
|
|
|
187
|
|
|
else: |
|
188
|
|
|
df[col] = df[col].astype("category") |
|
189
|
|
|
|
|
190
|
|
|
end_mem = df.memory_usage().sum() / 1024 ** 2 |
|
191
|
|
|
|
|
192
|
|
|
if show_reduction is True: |
|
193
|
|
|
print( |
|
194
|
|
|
"Reduced memory usage of DataFrame by " |
|
195
|
|
|
f"{(1 - end_mem/start_mem) * 100:.2f} %." |
|
196
|
|
|
) |
|
197
|
|
|
|
|
198
|
|
|
return df |
|
199
|
|
|
|
openego /
eGon-data
