Skip to content

How to Use PyZDC

get_alarm_severities(years=[2022, 2023], disease='CHIK', limit=None, verbose=False)

Retrieve alarm severities in treatment for a specified disease and years.

Parameters:

Name Type Description Default
years list[int]

List of years to retrieve data for.

 [2022, 2023]
disease str

Disease code to filter notifications.

 'CHIK'
limit int | None

Maximum number of records to retrieve.

 None
verbose bool

If True, enables verbose logging. Defaults to False.

 False

Returns:

Type Description
DataFrame

pd.DataFrame: DataFrame containing the notification data.
Example

df = get_alarm_severities([2021, 2022], "DENG", limit=100, verbose=True)

Source code in pyzdc/get_info/get_info.py 
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
@validate_verbose
def get_alarm_severities(
    years: list[int] = [2022, 2023],
    disease: str = "CHIK",
    limit: int | None = None,
    verbose: bool = False,
) -> pd.DataFrame:
    """
    Retrieve alarm severities in treatment for a specified disease and years.

    Args:
        years (list[int], optional): List of years to retrieve data for.
        Defaults to [2022, 2023].
        disease (str, optional): Disease code to filter notifications.
        Defaults to "CHIK".
        limit (int | None, optional): Maximum number of records to retrieve.
        Defaults to None.
        verbose (bool, optional): If True, enables verbose logging. Defaults to False.

    Returns:
        pd.DataFrame: DataFrame containing the notification data.

    Example:
        df = get_alarm_severities([2021, 2022], "DENG", limit=100, verbose=True)
    """
    return get_data_from_table("alarms_severities", years, disease, limit, verbose)

get_clinical_signs(years=[2022, 2023], disease='CHIK', limit=None, verbose=False)

Retrieve clinical signs data data for a specified disease and years.

Parameters:

Name Type Description Default
years list[int]

List of years to retrieve data for.

 [2022, 2023]
disease str

Disease code to filter notifications.

 'CHIK'
limit int | None

Maximum number of records to retrieve.

 None
verbose bool

If True, enables verbose logging. Defaults to False.

 False

Returns:

Type Description
DataFrame

pd.DataFrame: DataFrame containing the notification data.
Example

df = get_clinical_signs([2021, 2022], "DENG", limit=100, verbose=True)

Source code in pyzdc/get_info/get_info.py 
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
@validate_verbose
def get_clinical_signs(
    years: list[int] = [2022, 2023],
    disease: str = "CHIK",
    limit: int | None = None,
    verbose: bool = False,
) -> pd.DataFrame:
    """
    Retrieve clinical signs data data for a specified disease and years.

    Args:
        years (list[int], optional): List of years to retrieve data for.
        Defaults to [2022, 2023].
        disease (str, optional): Disease code to filter notifications.
        Defaults to "CHIK".
        limit (int | None, optional): Maximum number of records to retrieve.
        Defaults to None.
        verbose (bool, optional): If True, enables verbose logging. Defaults to False.

    Returns:
        pd.DataFrame: DataFrame containing the notification data.

    Example:
        df = get_clinical_signs([2021, 2022], "DENG", limit=100, verbose=True)
    """
    return get_data_from_table("clinical_signs", years, disease, limit, verbose)

get_data_from_table(table_name, years=[2022, 2023], disease='CHIK', limit=None, verbose=False)

Extracts data from a specified table, processes it, and returns it as a pandas DataFrame.

Parameters: table_name (str): The name of the table to load data from. years (list[int], optional): List of years to filter the data. Defaults to [2022, 2023]. disease (str, optional): Disease code to filter the data. Defaults to "CHIK". limit (int | None, optional): Maximum number of rows to load. If None, loads all rows. Defaults to None. verbose (bool, optional): If True, enables verbose logging. Defaults to False.

Returns: pd.DataFrame: The processed data as a pandas DataFrame. Returns an empty DataFrame if no data is available.

Example

df = get_data_from_table( "notifications_info", [2021, 2022], "DENG", limit=100, verbose=True )

Source code in pyzdc/get_info/get_info.py 
 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
@validate_verbose
def get_data_from_table( # noqa: C901
    table_name: str,
    years: List[int] = [2022, 2023],
    disease: str = "CHIK",
    limit: int | None = None,
    verbose: bool = False,
) -> pd.DataFrame:
    """
    Extracts data from a specified table, processes it, and returns it as a pandas
    DataFrame.

    Parameters:
    table_name (str): The name of the table to load data from.
    years (list[int], optional): List of years to filter the data. Defaults to [2022,
    2023].
    disease (str, optional): Disease code to filter the data. Defaults to "CHIK".
    limit (int | None, optional): Maximum number of rows to load. If None, loads all
    rows. Defaults to None.
    verbose (bool, optional): If True, enables verbose logging. Defaults to False.

    Returns:
    pd.DataFrame: The processed data as a pandas DataFrame. Returns an empty DataFrame
    if no data is available.

    Example:
        df = get_data_from_table(
            "notifications_info", [2021, 2022], "DENG", limit=100, verbose=True
        )
    """
    if not verbose:
        logging.disable(logging.CRITICAL)

    try:
        if disease not in VALID_DISEASES:
            valid_options = ", ".join(
                [f"{code}: {name}" for code, name in VALID_DISEASES.items()]
            )
            raise ValueError(
                f"Invalid disease code '{disease}'. Valid options are: {valid_options}"
            )

        extractor = Extractor()
        column_transformer = ColumnTransformer()
        db_transformer = DBTransformer()
        db_loader = Loader()
        db_refresher = Refresher()

        db_refresher.delete_database()

        sinan = SINAN().load()
        available_years = sorted(
            int(match.group(1)) + 2000
            for file in sinan.get_files(dis_code=[disease])
            if (match := re.search(r"BR(\d{2})", str(file)))
        )

        unavailable_years = [year for year in years if year not in available_years]
        if unavailable_years:
            raise ValueError(
                f"The following years are not available for disease {disease}: "
                f"{unavailable_years}"
            )

        files = extractor.extract_parquet(disease, years)
        if not files:
            raise ValueError(f"No data found for disease {disease} in years {years}")

        extractor.insert_parquet_to_duck(files)
        column_transformer.rename_db_columns()
        db_transformer.transform_db()
        data = db_loader.load_data(table_name=table_name, limit=limit)
        db_refresher.delete_database()

        data = data.dropna(axis=1, how="all")

        if data.empty or data.shape[1] == 0:
            logging.warning("No data available: All columns are empty or null.")
            return pd.DataFrame()

        data = data.dropna()

        if data.empty:
            logging.warning(
                "No data available: All rows are empty or null after filtering."
            )
            return pd.DataFrame()
    except ValueError as e:
        if "Unknown disease(s)" in str(e):
            valid_options = ", ".join(
                [f"{code}: {name}" for code, name in VALID_DISEASES.items()]
            )
            raise ValueError(
                f"Invalid disease code. Valid options are: {valid_options}"
            ) from None
        raise
    except CatalogException as ce:
        if "Table with name sinan does not exist" in str(ce):
            raise ValueError(
                f"No data found for disease {disease} in years {years}"
            ) from ce
        raise
    except Exception as e:
        raise ValueError(f"Error processing data: {str(e)}") from e
    finally:
        if not verbose:
            logging.disable(logging.NOTSET)

    return data

get_exams(years=[2022, 2023], disease='CHIK', limit=None, verbose=False)

Retrieve exams info for a specified disease and years.

Parameters:

Name Type Description Default
years list[int]

List of years to retrieve data for.

 [2022, 2023]
disease str

Disease code to filter notifications.

 'CHIK'
limit int | None

Maximum number of records to retrieve.

 None
verbose bool

If True, enables verbose logging. Defaults to False.

 False

Returns:

Type Description
DataFrame

pd.DataFrame: DataFrame containing the notification data.
Example

df = get_exams([2021, 2022], "DENG", limit=100, verbose=True)

Source code in pyzdc/get_info/get_info.py 
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
@validate_verbose
def get_exams(
    years: list[int] = [2022, 2023],
    disease: str = "CHIK",
    limit: int | None = None,
    verbose: bool = False,
) -> pd.DataFrame:
    """
    Retrieve exams info for a specified disease and years.

    Args:
        years (list[int], optional): List of years to retrieve data for.
        Defaults to [2022, 2023].
        disease (str, optional): Disease code to filter notifications.
        Defaults to "CHIK".
        limit (int | None, optional): Maximum number of records to retrieve.
        Defaults to None.
        verbose (bool, optional): If True, enables verbose logging. Defaults to False.

    Returns:
        pd.DataFrame: DataFrame containing the notification data.

    Example:
        df = get_exams([2021, 2022], "DENG", limit=100, verbose=True)
    """
    return get_data_from_table("exams", years, disease, limit, verbose)

get_hospital_info(years=[2022, 2023], disease='CHIK', limit=None, verbose=False)

Retrieve hospital info for a specified disease and years.

Parameters:

Name Type Description Default
years list[int]

List of years to retrieve data for.

 [2022, 2023]
disease str

Disease code to filter notifications.

 'CHIK'
limit int | None

Maximum number of records to retrieve.

 None
verbose bool

If True, enables verbose logging. Defaults to False.

 False

Returns:

Type Description
DataFrame

pd.DataFrame: DataFrame containing the notification data.
Example

df = get_hospital_info([2021, 2022], "DENG", limit=100, verbose=True)

Source code in pyzdc/get_info/get_info.py 
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
@validate_verbose
def get_hospital_info(
    years: list[int] = [2022, 2023],
    disease: str = "CHIK",
    limit: int | None = None,
    verbose: bool = False,
) -> pd.DataFrame:
    """
    Retrieve hospital info for a specified disease and years.

    Args:
        years (list[int], optional): List of years to retrieve data for.
        Defaults to [2022, 2023].
        disease (str, optional): Disease code to filter notifications.
        Defaults to "CHIK".
        limit (int | None, optional): Maximum number of records to retrieve.
        Defaults to None.
        verbose (bool, optional): If True, enables verbose logging. Defaults to False.

    Returns:
        pd.DataFrame: DataFrame containing the notification data.

    Example:
        df = get_hospital_info([2021, 2022], "DENG", limit=100, verbose=True)
    """
    return get_data_from_table("hospital_info", years, disease, limit, verbose)

get_notifications(years=[2022, 2023], disease='CHIK', limit=None, verbose=False)

Retrieve notification data for a specified disease and years.

Parameters:

Name Type Description Default
years list[int]

List of years to retrieve data for. Defaults to

 [2022, 2023]
disease str

Disease code to filter notifications.

 'CHIK'
limit int | None

Maximum number of records to retrieve. Defaults

 None
verbose bool

If True, enables verbose logging. Defaults to False.

 False

Returns:

Type Description
DataFrame

pd.DataFrame: DataFrame containing the notification data.
Example

df = get_notifications([2021, 2022], "DENG", limit=100, verbose=True)

Source code in pyzdc/get_info/get_info.py 
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
@validate_verbose
def get_notifications(
    years: list[int] = [2022, 2023],
    disease: str = "CHIK",
    limit: int | None = None,
    verbose: bool = False,
) -> pd.DataFrame:
    """
    Retrieve notification data for a specified disease and years.

    Args:
        years (list[int], optional): List of years to retrieve data for. Defaults to
        [2022, 2023].
        disease (str, optional): Disease code to filter notifications.
        Defaults to "CHIK".
        limit (int | None, optional): Maximum number of records to retrieve. Defaults
        to None.
        verbose (bool, optional): If True, enables verbose logging. Defaults to False.

    Returns:
        pd.DataFrame: DataFrame containing the notification data.

    Example:
        df = get_notifications([2021, 2022], "DENG", limit=100, verbose=True)
    """
    return get_data_from_table("notifications_info", years, disease, limit, verbose)

get_patient_diseases(years=[2022, 2023], disease='CHIK', limit=None, verbose=False)

Retrieve patient diseases for a specified disease and years.

Parameters:

Name Type Description Default
years list[int]

List of years to retrieve data for. Defaults to

 [2022, 2023]
disease str

Disease code to filter notifications.

 'CHIK'
limit int | None

Maximum number of records to retrieve.

 None
verbose bool

If True, enables verbose logging. Defaults to False.

 False

Returns:

Type Description
DataFrame

pd.DataFrame: DataFrame containing the notification data.
Example

df = get_patient_diseases([2021, 2022], "DENG", limit=100, verbose=True)

Source code in pyzdc/get_info/get_info.py 
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
@validate_verbose
def get_patient_diseases(
    years: list[int] = [2022, 2023],
    disease: str = "CHIK",
    limit: int | None = None,
    verbose: bool = False,
) -> pd.DataFrame:
    """
    Retrieve patient diseases for a specified disease and years.

    Args:
        years (list[int], optional): List of years to retrieve data for. Defaults to
        [2022, 2023].
        disease (str, optional): Disease code to filter notifications.
        Defaults to "CHIK".
        limit (int | None, optional): Maximum number of records to retrieve.
        Defaults to None.
        verbose (bool, optional): If True, enables verbose logging. Defaults to False.

    Returns:
        pd.DataFrame: DataFrame containing the notification data.

    Example:
        df = get_patient_diseases([2021, 2022], "DENG", limit=100, verbose=True)
    """
    return get_data_from_table("patient_diseases", years, disease, limit, verbose)

get_personal_data(years=[2022, 2023], disease='CHIK', limit=None, verbose=False)

Retrieve patients personal data for a specified disease and years.

Parameters:

Name Type Description Default
years list[int]

List of years to retrieve data for. Defaults to

 [2022, 2023]
disease str

Disease code to filter notifications.

 'CHIK'
limit int | None

Maximum number of records to retrieve.

 None
verbose bool

If True, enables verbose logging. Defaults to False.

 False

Returns:

Type Description
DataFrame

pd.DataFrame: DataFrame containing the notification data.
Example

df = get_personal_data([2021, 2022], "DENG", limit=100, verbose=True)

Source code in pyzdc/get_info/get_info.py 
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
@validate_verbose
def get_personal_data(
    years: list[int] = [2022, 2023],
    disease: str = "CHIK",
    limit: int | None = None,
    verbose: bool = False,
) -> pd.DataFrame:
    """
    Retrieve patients personal data for a specified disease and years.

    Args:
        years (list[int], optional): List of years to retrieve data for. Defaults to
        [2022, 2023].
        disease (str, optional): Disease code to filter notifications.
        Defaults to "CHIK".
        limit (int | None, optional): Maximum number of records to retrieve.
        Defaults to None.
        verbose (bool, optional): If True, enables verbose logging. Defaults to False.

    Returns:
        pd.DataFrame: DataFrame containing the notification data.

    Example:
        df = get_personal_data([2021, 2022], "DENG", limit=100, verbose=True)
    """
    return get_data_from_table("personal_data", years, disease, limit, verbose)

get_sinan_info(years=[2022, 2023], disease='CHIK', limit=None, verbose=False)

Retrieve sinal internal info for a specified disease and years.

Parameters:

Name Type Description Default
years list[int]

List of years to retrieve data for.

 [2022, 2023]
disease str

Disease code to filter notifications.

 'CHIK'
limit int | None

Maximum number of records to retrieve.

 None
verbose bool

If True, enables verbose logging. Defaults to False.

 False

Returns:

Type Description
DataFrame

pd.DataFrame: DataFrame containing the notification data.
Example

df = get_sinan_info([2021, 2022], "DENG", limit=100, verbose=True)

Source code in pyzdc/get_info/get_info.py 
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
@validate_verbose
def get_sinan_info(
    years: list[int] = [2022, 2023],
    disease: str = "CHIK",
    limit: int | None = None,
    verbose: bool = False,
) -> pd.DataFrame:
    """
    Retrieve sinal internal info for a specified disease and years.

    Args:
        years (list[int], optional): List of years to retrieve data for.
        Defaults to [2022, 2023].
        disease (str, optional): Disease code to filter notifications.
        Defaults to "CHIK".
        limit (int | None, optional): Maximum number of records to retrieve.
        Defaults to None.
        verbose (bool, optional): If True, enables verbose logging. Defaults to False.

    Returns:
        pd.DataFrame: DataFrame containing the notification data.

    Example:
        df = get_sinan_info([2021, 2022], "DENG", limit=100, verbose=True)
    """
    return get_data_from_table("sinan_internal_info", years, disease, limit, verbose)

get_years(disease='CHIK')

Extract available years from disease-related files.

Parameters:

Name Type Description Default
disease str

Disease code. Allowed values are "DENG", "ZIKA", and "CHIK".

 'CHIK'

Returns:

Name Type Description
str None

Error message if an invalid disease is provided.
str None

Message listing the available years for the specified disease.
Example

get_years("DENG")

Source code in pyzdc/get_info/get_info.py 
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
def get_years(disease: str = "CHIK") -> None:
    """
    Extract available years from disease-related files.

    Args:
        disease (str): Disease code. Allowed values are "DENG", "ZIKA", and "CHIK".

    Returns:
        str: Error message if an invalid disease is provided.
        str: Message listing the available years for the specified disease.

    Example:
        get_years("DENG")
    """

    sinan = SINAN().load()

    valid_diseases = {"DENG": "dengue", "ZIKA": "zika", "CHIK": "chikungunya"}

    if disease not in valid_diseases:
        return print("Error: Only DENG, ZIKA, and CHIK are allowed.")

    years = sorted(
        int(match.group(1)) + 2000
        for file in sinan.get_files(dis_code=[disease])
        if (match := re.search(r"BR(\d{2})", str(file)))
    )

    available_disease = valid_diseases[disease]
    available_years = ", ".join(map(str, years))

    available_disease = valid_diseases[disease]
    if years:
        available_years = (
            f"from {years[0]} to {years[-1]}" if len(years) > 1 else f"in {years[0]}"
        )
    else:
        available_years = "no available data"

    return print(f"The available data for {available_disease} is {available_years}.")

Conclusion

PyZDC makes it easy to extract and analyze epidemiological data. Whether you are a beginner or an advanced user, these functions help you get insights quickly.

For more details, visit: GitHub Repository.