Skip to content

Tools > Collectors

Data Collectors.

This module provides utility functions for data collection.

StationDataCollector

Data collector for weather stations in Brazil.

This class is designed to collect, validate, transform, and save data from CSV files related to weather stations across Brazil. It utilizes a Pydantic model for data validation to ensure the integrity and accuracy of the data collected.

Parameters:

input_folder : str Directory containing the source CSV files. output_path : str Directory where processed files will be saved. file_name : str Base name for the output file. column_names : Dict[str, str] Mapping from original column names to desired column names. schema : BaseModel Pydantic model used for validating the data.

Attributes:

_input_folder : str Input directory for source CSV files. _output_path : str Output directory for processed data. _file_name : str Base name for the output file. _schema : BaseModel Pydantic model for data validation. _column_names : Dict[str, str] Column name mapping.

Source code in app/tools/collectors.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
 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
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
203
204
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
231
232
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
259
260
261
262
263
264
265
266
267
class StationDataCollector:
    """Data collector for weather stations in Brazil.

    This class is designed to collect, validate, transform, and save data from
    CSV files related to weather stations across Brazil. It utilizes a
    Pydantic model for data validation to ensure the integrity and accuracy
    of the data collected.

    Parameters:
    ----------
    input_folder : str
        Directory containing the source CSV files.
    output_path : str
        Directory where processed files will be saved.
    file_name : str
        Base name for the output file.
    column_names : Dict[str, str]
        Mapping from original column names to desired column names.
    schema : BaseModel
        Pydantic model used for validating the data.

    Attributes:
    ----------
    _input_folder : str
        Input directory for source CSV files.
    _output_path : str
        Output directory for processed data.
    _file_name : str
        Base name for the output file.
    _schema : BaseModel
        Pydantic model for data validation.
    _column_names : Dict[str, str]
        Column name mapping.
    """

    def __init__(
        self,
        input_folder: str,
        output_path: str,
        file_name: str,
        column_names: Dict[str, str],
        schema,
    ):
        """Initialize a new StationDataCollector instance.

        Parameters:
        ----------
        input_folder : str
            Directory containing the source CSV files.
        output_path : str
            Directory where processed files will be saved.
        file_name : str
            Base name for the output file.
        column_names : Dict[str, str]
            Mapping from original column names to desired column names.
        schema : BaseModel
            Pydantic model used for validating the data.
        """
        self._input_folder = input_folder
        self._output_path = output_path
        self._file_name = file_name
        self._schema = schema
        self._column_names = column_names

    def start(self):
        """Initiate the data collection process.

        This method orchestrates the workflow of data collection including
        retrieving, validating, transforming, and storing data.
        """
        response, data_files = self.get_data()

        self.validate_data(response)

        response = self.transform_data(
            response,
            self._column_names,
            self._output_path,
            data_files,
        )

        self.load_data(
            response,
            self._output_path,
            self._file_name,
        )

    @logger_decorator
    def get_data(self) -> Tuple[List[pd.DataFrame], List[str]]:
        """Get data from CSV files.

        Returns:
        -------
        tuple[List[pd.DataFrame], List[str]]
            A tuple containing a list of DataFrames representing the data and
            a list of strings representing the file names.

        Raises:
        ------
        ValueError
            If no CSV files are found in the specified directory.
        """
        # Collecting all CSV file paths from the input folder
        data_files = glob.glob(os.path.join(self._input_folder, "*.csv"))
        data_files.extend(glob.glob(os.path.join(self._input_folder, "*.CSV")))
        if not data_files:
            raise ValueError("No CSV files found in the specified folder.")

        all_data = [
            pd.read_csv(
                file,
                encoding="latin-1",
                nrows=8,
                sep=";",
                header=None,
                decimal=",",
                index_col=0,
            ).T
            for file in data_files[:100]
        ]

        return all_data, data_files

    @logger_decorator
    def validate_data(self, all_data: List[pd.DataFrame]) -> None:
        """Validate the structure of the collected data.

        Parameters:
        ----------
        all_data : List[pd.DataFrame]
            List of DataFrames to be validated.

        Raises:
        ------
        ValueError
            If the structure of any DataFrame is inconsistent.
        """
        list_columns = [df.columns.to_list() for df in all_data]
        validate_sublists(list_columns)

    @logger_decorator
    def transform_data(
        self,
        all_data: List[pd.DataFrame],
        column_names: Dict[str, str],
        output_path: str,
        data_files: List[str],
    ) -> pd.DataFrame:
        """Transform and validate the collected data.

        Parameters:
        ----------
        all_data : List[pd.DataFrame]
            List of DataFrames to be transformed.
        column_names : Dict[str, str]
            Mapping of original column names to new names.
        output_path : str
            Path to the folder where the processed data will be saved.
        data_files : List[str]
            List of file names being processed.

        Returns:
        -------
        pd.DataFrame
            Concatenated and validated DataFrame.

        Raises:
        ------
        Exception
            If all collected data is invalid.
        """
        files_processing = len(all_data)
        logger.info(f"Total files to process = {files_processing:,}")

        logger.info("Analyzing data quality")
        process_data = []
        good_df = pd.DataFrame()
        for i, df in enumerate(all_data):
            logger.info(f"Files to process: {files_processing-i:,}")

            file_name_process = data_files[i].split("/")[-1]
            file_log = file_name_process.replace(".", "_")

            df = df.rename(columns=column_names)
            good_data = list(
                validate_data_quality(
                    df,
                    output_path,
                    file_log,
                    self._schema,
                ),
            )
            if good_data:
                good_df = pd.DataFrame(good_data)
                process_data.append(good_df)
            else:
                good_df = pd.DataFrame()

        logger.info("Data validation finished")

        # Avoiding concatenating empty dataframes and warnings from Pandas
        process_data_filtered = [
            df for df in process_data if not df.empty and not df.isna().all().all()
        ]
        if process_data_filtered:
            validate_data = pd.concat(process_data_filtered)
            validate_data = validate_data.drop_duplicates(["IdStationWho"])
            return validate_data
        else:
            raise Exception("All collected data was invalid.")

    @logger_decorator
    def load_data(
        self,
        validate_data: pd.DataFrame,
        load_path: str,
        file_name: str,
    ) -> None:
        """Save the validated data to a Parquet file.

        Parameters:
        ----------
        validate_data : pd.DataFrame
            DataFrame containing validated station data.
        load_path : str
            Path to the folder where the Parquet file will be saved.
        file_name : str
            Name of the output file without the extension.

        Raises:
        ------
        Exception
            If there is an error converting data to Parquet.
        """
        try:
            validate_data.to_parquet(
                os.path.join(
                    load_path,
                    file_name + ".parquet",
                ),
                index=False,
            )
        except Exception as e:
            print(f"Error to convert data to parquet: {e}")

__init__(input_folder, output_path, file_name, column_names, schema)

Initialize a new StationDataCollector instance.

Parameters:

input_folder : str Directory containing the source CSV files. output_path : str Directory where processed files will be saved. file_name : str Base name for the output file. column_names : Dict[str, str] Mapping from original column names to desired column names. schema : BaseModel Pydantic model used for validating the data.

Source code in app/tools/collectors.py 
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
def __init__(
    self,
    input_folder: str,
    output_path: str,
    file_name: str,
    column_names: Dict[str, str],
    schema,
):
    """Initialize a new StationDataCollector instance.

    Parameters:
    ----------
    input_folder : str
        Directory containing the source CSV files.
    output_path : str
        Directory where processed files will be saved.
    file_name : str
        Base name for the output file.
    column_names : Dict[str, str]
        Mapping from original column names to desired column names.
    schema : BaseModel
        Pydantic model used for validating the data.
    """
    self._input_folder = input_folder
    self._output_path = output_path
    self._file_name = file_name
    self._schema = schema
    self._column_names = column_names

get_data()

Get data from CSV files.

Returns:

tuple[List[pd.DataFrame], List[str]] A tuple containing a list of DataFrames representing the data and a list of strings representing the file names.

Raises:

ValueError If no CSV files are found in the specified directory.

Source code in app/tools/collectors.py 
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
@logger_decorator
def get_data(self) -> Tuple[List[pd.DataFrame], List[str]]:
    """Get data from CSV files.

    Returns:
    -------
    tuple[List[pd.DataFrame], List[str]]
        A tuple containing a list of DataFrames representing the data and
        a list of strings representing the file names.

    Raises:
    ------
    ValueError
        If no CSV files are found in the specified directory.
    """
    # Collecting all CSV file paths from the input folder
    data_files = glob.glob(os.path.join(self._input_folder, "*.csv"))
    data_files.extend(glob.glob(os.path.join(self._input_folder, "*.CSV")))
    if not data_files:
        raise ValueError("No CSV files found in the specified folder.")

    all_data = [
        pd.read_csv(
            file,
            encoding="latin-1",
            nrows=8,
            sep=";",
            header=None,
            decimal=",",
            index_col=0,
        ).T
        for file in data_files[:100]
    ]

    return all_data, data_files

load_data(validate_data, load_path, file_name)

Save the validated data to a Parquet file.

Parameters:

validate_data : pd.DataFrame DataFrame containing validated station data. load_path : str Path to the folder where the Parquet file will be saved. file_name : str Name of the output file without the extension.

Raises:

Exception If there is an error converting data to Parquet.

Source code in app/tools/collectors.py 
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
@logger_decorator
def load_data(
    self,
    validate_data: pd.DataFrame,
    load_path: str,
    file_name: str,
) -> None:
    """Save the validated data to a Parquet file.

    Parameters:
    ----------
    validate_data : pd.DataFrame
        DataFrame containing validated station data.
    load_path : str
        Path to the folder where the Parquet file will be saved.
    file_name : str
        Name of the output file without the extension.

    Raises:
    ------
    Exception
        If there is an error converting data to Parquet.
    """
    try:
        validate_data.to_parquet(
            os.path.join(
                load_path,
                file_name + ".parquet",
            ),
            index=False,
        )
    except Exception as e:
        print(f"Error to convert data to parquet: {e}")

start()

Initiate the data collection process.

This method orchestrates the workflow of data collection including retrieving, validating, transforming, and storing data.

Source code in app/tools/collectors.py 
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
def start(self):
    """Initiate the data collection process.

    This method orchestrates the workflow of data collection including
    retrieving, validating, transforming, and storing data.
    """
    response, data_files = self.get_data()

    self.validate_data(response)

    response = self.transform_data(
        response,
        self._column_names,
        self._output_path,
        data_files,
    )

    self.load_data(
        response,
        self._output_path,
        self._file_name,
    )

transform_data(all_data, column_names, output_path, data_files)

Transform and validate the collected data.

Parameters:

all_data : List[pd.DataFrame] List of DataFrames to be transformed. column_names : Dict[str, str] Mapping of original column names to new names. output_path : str Path to the folder where the processed data will be saved. data_files : List[str] List of file names being processed.

Returns:

pd.DataFrame Concatenated and validated DataFrame.

Raises:

Exception If all collected data is invalid.

Source code in app/tools/collectors.py 
164
165
166
167
168
169
170
171
172
173
174
175
176
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
203
204
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
231
232
233
@logger_decorator
def transform_data(
    self,
    all_data: List[pd.DataFrame],
    column_names: Dict[str, str],
    output_path: str,
    data_files: List[str],
) -> pd.DataFrame:
    """Transform and validate the collected data.

    Parameters:
    ----------
    all_data : List[pd.DataFrame]
        List of DataFrames to be transformed.
    column_names : Dict[str, str]
        Mapping of original column names to new names.
    output_path : str
        Path to the folder where the processed data will be saved.
    data_files : List[str]
        List of file names being processed.

    Returns:
    -------
    pd.DataFrame
        Concatenated and validated DataFrame.

    Raises:
    ------
    Exception
        If all collected data is invalid.
    """
    files_processing = len(all_data)
    logger.info(f"Total files to process = {files_processing:,}")

    logger.info("Analyzing data quality")
    process_data = []
    good_df = pd.DataFrame()
    for i, df in enumerate(all_data):
        logger.info(f"Files to process: {files_processing-i:,}")

        file_name_process = data_files[i].split("/")[-1]
        file_log = file_name_process.replace(".", "_")

        df = df.rename(columns=column_names)
        good_data = list(
            validate_data_quality(
                df,
                output_path,
                file_log,
                self._schema,
            ),
        )
        if good_data:
            good_df = pd.DataFrame(good_data)
            process_data.append(good_df)
        else:
            good_df = pd.DataFrame()

    logger.info("Data validation finished")

    # Avoiding concatenating empty dataframes and warnings from Pandas
    process_data_filtered = [
        df for df in process_data if not df.empty and not df.isna().all().all()
    ]
    if process_data_filtered:
        validate_data = pd.concat(process_data_filtered)
        validate_data = validate_data.drop_duplicates(["IdStationWho"])
        return validate_data
    else:
        raise Exception("All collected data was invalid.")

validate_data(all_data)

Validate the structure of the collected data.

Parameters:

all_data : List[pd.DataFrame] List of DataFrames to be validated.

Raises:

ValueError If the structure of any DataFrame is inconsistent.

Source code in app/tools/collectors.py 
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
@logger_decorator
def validate_data(self, all_data: List[pd.DataFrame]) -> None:
    """Validate the structure of the collected data.

    Parameters:
    ----------
    all_data : List[pd.DataFrame]
        List of DataFrames to be validated.

    Raises:
    ------
    ValueError
        If the structure of any DataFrame is inconsistent.
    """
    list_columns = [df.columns.to_list() for df in all_data]
    validate_sublists(list_columns)

WeatherDataCollector

Data collector for weather in Brazil.

This class is designed to collect, validate, transform, and save data from CSV files related to weather stations across Brazil. It utilizes a Pydantic model for data validation to ensure the integrity and accuracy of the data collected.

Parameters:

input_folder : str Directory containing the source CSV files. output_path : str Directory where processed files will be saved. file_name : str Base name for the output file. column_names : Dict[str, str] Mapping from original column names to desired column names. schema : BaseModel Pydantic model used for validating the data.

Attributes:

_input_folder : str Input directory for source CSV files. _output_path : str Output directory for processed data. _file_name : str Base name for the output file. _schema : BaseModel Pydantic model for data validation. _column_names : Dict[str, str] Column name mapping.

Source code in app/tools/collectors.py 
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
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
315
316
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
343
344
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
371
372
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
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
class WeatherDataCollector:
    """Data collector for weather in Brazil.

    This class is designed to collect, validate, transform, and save data from
    CSV files related to weather stations across Brazil. It utilizes a
    Pydantic model for data validation to ensure the integrity and accuracy
    of the data collected.

    Parameters:
    ----------
    input_folder : str
        Directory containing the source CSV files.
    output_path : str
        Directory where processed files will be saved.
    file_name : str
        Base name for the output file.
    column_names : Dict[str, str]
        Mapping from original column names to desired column names.
    schema : BaseModel
        Pydantic model used for validating the data.

    Attributes:
    ----------
    _input_folder : str
        Input directory for source CSV files.
    _output_path : str
        Output directory for processed data.
    _file_name : str
        Base name for the output file.
    _schema : BaseModel
        Pydantic model for data validation.
    _column_names : Dict[str, str]
        Column name mapping.
    """

    def __init__(
        self,
        input_folder: str,
        output_path: str,
        file_name: str,
        column_names: Dict[str, str],
        schema,
    ):
        """Initialize a new StationDataCollector instance.

        Parameters:
        ----------
        input_folder : str
            Directory containing the source CSV files.
        output_path : str
            Directory where processed files will be saved.
        file_name : str
            Base name for the output file.
        column_names : Dict[str, str]
            Mapping from original column names to desired column names.
        schema : BaseModel
            Pydantic model used for validating the data.
        """
        self._input_folder = input_folder
        self._output_path = output_path
        self._file_name = file_name
        self._schema = schema
        self._column_names = column_names

    def start(self):
        """Initiate the data collection process.

        This method orchestrates the workflow of data collection including
        retrieving, validating, transforming, and storing data.
        """
        response, data_files = self.get_data()

        self.validate_data(response)

        response = self.transform_data(
            response,
            self._column_names,
            self._output_path,
            data_files,
        )

        self.load_data(
            response,
            self._output_path,
            self._file_name,
        )

    @logger_decorator
    def get_data(self) -> tuple[List[pd.DataFrame], List[str]]:
        """Get data from CSV files.

        Returns:
        -------
        tuple[List[pd.DataFrame], List[str]]
            A tuple containing a list of DataFrames representing the data and
            a list of strings representing the file names.

        Raises:
        ------
        ValueError
            If no CSV files are found in the specified directory.
        """
        # Collecting all CSV file paths from the input folder
        data_files = glob.glob(os.path.join(self._input_folder, "*.csv"))
        data_files.extend(glob.glob(os.path.join(self._input_folder, "*.CSV")))
        if not data_files:
            raise ValueError("No CSV files found in the specified folder.")

        all_data = [
            pd.read_csv(
                file,
                encoding="latin-1",
                skiprows=8,
                sep=";",
                usecols=[x for x in range(0, 19)],
                na_values=["-9999"],
                dtype=str,
            )
            for file in data_files[:100]
        ]

        stations_data = [
            pd.read_csv(
                file,
                encoding="latin-1",
                nrows=8,
                sep=";",
                header=None,
                decimal=",",
                index_col=0,
            ).T
            for file in data_files[:100]
        ]

        for i, df in enumerate(all_data):
            df["IdStationWho"] = stations_data[i].loc[
                1,
                "CODIGO (WMO):",
            ]

        return all_data, data_files

    @logger_decorator
    def validate_data(self, all_data: List[pd.DataFrame]) -> None:
        """Validate the structure of the collected data.

        Parameters:
        ----------
        all_data : List[pd.DataFrame]
            List of DataFrames to be validated.

        Raises:
        ------
        ValueError
            If the structure of any DataFrame is inconsistent.
        """
        list_columns = [df.columns.to_list() for df in all_data]
        validate_sublists(list_columns)

    @logger_decorator
    def transform_data(
        self,
        all_data: List[pd.DataFrame],
        column_names: Dict[str, str],
        output_path: str,
        data_files: List[str],
    ) -> pd.DataFrame:
        """Transform and validate the collected data.

        Parameters:
        ----------
        all_data : List[pd.DataFrame]
            List of DataFrames to be transformed.
        column_names : Dict[str, str]
            Mapping of original column names to new names.
        output_path : str
            Path to the folder where the processed data will be saved.
        data_files : List[str]
            List of file names being processed.

        Returns:
        -------
        pd.DataFrame
            Concatenated and validated DataFrame.

        Raises:
        ------
        Exception
            If all collected data is invalid.
        """
        files_processing = len(all_data)
        logger.info(f"Total files to process = {files_processing:,}")

        logger.info("Analyzing data quality")
        process_data = []
        good_df = pd.DataFrame()
        for i, df in enumerate(all_data):
            logger.info(f"Files to process: {files_processing-i:,}")

            file_name_process = data_files[i].split("/")[-1]
            file_log = file_name_process.replace(".", "_")

            df = df.rename(columns=column_names)
            good_data = list(
                validate_data_quality(
                    df,
                    output_path,
                    file_log,
                    self._schema,
                ),
            )
            if good_data:
                good_df = pd.DataFrame(good_data)
                process_data.append(good_df)
            else:
                good_df = pd.DataFrame()

        logger.info("Data validation finished")

        # Avoiding concatenating empty dataframes and warnings from Pandas
        process_data_filtered = [
            df for df in process_data if not df.empty and not df.isna().all().all()
        ]
        if process_data_filtered:
            validate_data = pd.concat(process_data_filtered)
            return validate_data
        else:
            raise Exception("All collected data was invalid.")

    @logger_decorator
    def load_data(
        self,
        validate_data: pd.DataFrame,
        load_path: str,
        file_name: str,
    ) -> None:
        """Save the validated data to a Parquet file.

        Parameters:
        ----------
        validate_data : pd.DataFrame
            DataFrame containing validated station data.
        load_path : str
            Path to the folder where the Parquet file will be saved.
        file_name : str
            Name of the output file without the extension.

        Raises:
        ------
        Exception
            If there is an error converting data to Parquet.
        """
        try:
            validate_data.to_parquet(
                os.path.join(
                    load_path,
                    file_name + ".parquet",
                ),
                index=False,
            )
        except Exception as e:
            print(f"Error to convert data to parquet: {e}")

__init__(input_folder, output_path, file_name, column_names, schema)

Initialize a new StationDataCollector instance.

Parameters:

input_folder : str Directory containing the source CSV files. output_path : str Directory where processed files will be saved. file_name : str Base name for the output file. column_names : Dict[str, str] Mapping from original column names to desired column names. schema : BaseModel Pydantic model used for validating the data.

Source code in app/tools/collectors.py 
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
def __init__(
    self,
    input_folder: str,
    output_path: str,
    file_name: str,
    column_names: Dict[str, str],
    schema,
):
    """Initialize a new StationDataCollector instance.

    Parameters:
    ----------
    input_folder : str
        Directory containing the source CSV files.
    output_path : str
        Directory where processed files will be saved.
    file_name : str
        Base name for the output file.
    column_names : Dict[str, str]
        Mapping from original column names to desired column names.
    schema : BaseModel
        Pydantic model used for validating the data.
    """
    self._input_folder = input_folder
    self._output_path = output_path
    self._file_name = file_name
    self._schema = schema
    self._column_names = column_names

get_data()

Get data from CSV files.

Returns:

tuple[List[pd.DataFrame], List[str]] A tuple containing a list of DataFrames representing the data and a list of strings representing the file names.

Raises:

ValueError If no CSV files are found in the specified directory.

Source code in app/tools/collectors.py 
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
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
399
400
401
402
403
404
405
406
407
408
409
410
@logger_decorator
def get_data(self) -> tuple[List[pd.DataFrame], List[str]]:
    """Get data from CSV files.

    Returns:
    -------
    tuple[List[pd.DataFrame], List[str]]
        A tuple containing a list of DataFrames representing the data and
        a list of strings representing the file names.

    Raises:
    ------
    ValueError
        If no CSV files are found in the specified directory.
    """
    # Collecting all CSV file paths from the input folder
    data_files = glob.glob(os.path.join(self._input_folder, "*.csv"))
    data_files.extend(glob.glob(os.path.join(self._input_folder, "*.CSV")))
    if not data_files:
        raise ValueError("No CSV files found in the specified folder.")

    all_data = [
        pd.read_csv(
            file,
            encoding="latin-1",
            skiprows=8,
            sep=";",
            usecols=[x for x in range(0, 19)],
            na_values=["-9999"],
            dtype=str,
        )
        for file in data_files[:100]
    ]

    stations_data = [
        pd.read_csv(
            file,
            encoding="latin-1",
            nrows=8,
            sep=";",
            header=None,
            decimal=",",
            index_col=0,
        ).T
        for file in data_files[:100]
    ]

    for i, df in enumerate(all_data):
        df["IdStationWho"] = stations_data[i].loc[
            1,
            "CODIGO (WMO):",
        ]

    return all_data, data_files

load_data(validate_data, load_path, file_name)

Save the validated data to a Parquet file.

Parameters:

validate_data : pd.DataFrame DataFrame containing validated station data. load_path : str Path to the folder where the Parquet file will be saved. file_name : str Name of the output file without the extension.

Raises:

Exception If there is an error converting data to Parquet.

Source code in app/tools/collectors.py 
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
@logger_decorator
def load_data(
    self,
    validate_data: pd.DataFrame,
    load_path: str,
    file_name: str,
) -> None:
    """Save the validated data to a Parquet file.

    Parameters:
    ----------
    validate_data : pd.DataFrame
        DataFrame containing validated station data.
    load_path : str
        Path to the folder where the Parquet file will be saved.
    file_name : str
        Name of the output file without the extension.

    Raises:
    ------
    Exception
        If there is an error converting data to Parquet.
    """
    try:
        validate_data.to_parquet(
            os.path.join(
                load_path,
                file_name + ".parquet",
            ),
            index=False,
        )
    except Exception as e:
        print(f"Error to convert data to parquet: {e}")

start()

Initiate the data collection process.

This method orchestrates the workflow of data collection including retrieving, validating, transforming, and storing data.

Source code in app/tools/collectors.py 
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
def start(self):
    """Initiate the data collection process.

    This method orchestrates the workflow of data collection including
    retrieving, validating, transforming, and storing data.
    """
    response, data_files = self.get_data()

    self.validate_data(response)

    response = self.transform_data(
        response,
        self._column_names,
        self._output_path,
        data_files,
    )

    self.load_data(
        response,
        self._output_path,
        self._file_name,
    )

transform_data(all_data, column_names, output_path, data_files)

Transform and validate the collected data.

Parameters:

all_data : List[pd.DataFrame] List of DataFrames to be transformed. column_names : Dict[str, str] Mapping of original column names to new names. output_path : str Path to the folder where the processed data will be saved. data_files : List[str] List of file names being processed.

Returns:

pd.DataFrame Concatenated and validated DataFrame.

Raises:

Exception If all collected data is invalid.

Source code in app/tools/collectors.py 
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
@logger_decorator
def transform_data(
    self,
    all_data: List[pd.DataFrame],
    column_names: Dict[str, str],
    output_path: str,
    data_files: List[str],
) -> pd.DataFrame:
    """Transform and validate the collected data.

    Parameters:
    ----------
    all_data : List[pd.DataFrame]
        List of DataFrames to be transformed.
    column_names : Dict[str, str]
        Mapping of original column names to new names.
    output_path : str
        Path to the folder where the processed data will be saved.
    data_files : List[str]
        List of file names being processed.

    Returns:
    -------
    pd.DataFrame
        Concatenated and validated DataFrame.

    Raises:
    ------
    Exception
        If all collected data is invalid.
    """
    files_processing = len(all_data)
    logger.info(f"Total files to process = {files_processing:,}")

    logger.info("Analyzing data quality")
    process_data = []
    good_df = pd.DataFrame()
    for i, df in enumerate(all_data):
        logger.info(f"Files to process: {files_processing-i:,}")

        file_name_process = data_files[i].split("/")[-1]
        file_log = file_name_process.replace(".", "_")

        df = df.rename(columns=column_names)
        good_data = list(
            validate_data_quality(
                df,
                output_path,
                file_log,
                self._schema,
            ),
        )
        if good_data:
            good_df = pd.DataFrame(good_data)
            process_data.append(good_df)
        else:
            good_df = pd.DataFrame()

    logger.info("Data validation finished")

    # Avoiding concatenating empty dataframes and warnings from Pandas
    process_data_filtered = [
        df for df in process_data if not df.empty and not df.isna().all().all()
    ]
    if process_data_filtered:
        validate_data = pd.concat(process_data_filtered)
        return validate_data
    else:
        raise Exception("All collected data was invalid.")

validate_data(all_data)

Validate the structure of the collected data.

Parameters:

all_data : List[pd.DataFrame] List of DataFrames to be validated.

Raises:

ValueError If the structure of any DataFrame is inconsistent.

Source code in app/tools/collectors.py 
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
@logger_decorator
def validate_data(self, all_data: List[pd.DataFrame]) -> None:
    """Validate the structure of the collected data.

    Parameters:
    ----------
    all_data : List[pd.DataFrame]
        List of DataFrames to be validated.

    Raises:
    ------
    ValueError
        If the structure of any DataFrame is inconsistent.
    """
    list_columns = [df.columns.to_list() for df in all_data]
    validate_sublists(list_columns)

collect_years_list(list_years)

Extract the valid years from a list.

This function collects years beginning in 2000 and ending in the year from the last month. It filters out any years that are not integers or are outside the valid range.

Parameters

list_years : List[int] List with the years that will be processed.

Returns

List[int] A list containing only the valid years within the specified range.

Raises

ValueError If the list is empty or contains no valid years.

Source code in app/tools/collectors.py 
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
def collect_years_list(
    list_years: List[int],
) -> List[int]:
    """Extract the valid years from a list.

    This function collects years beginning in 2000 and ending in the
    year from the last month. It filters out any years that are not
    integers or are outside the valid range.

    Parameters
    ----------
    list_years : List[int]
        List with the years that will be processed.

    Returns
    -------
    List[int]
        A list containing only the valid years within the specified range.

    Raises
    ------
    ValueError
        If the list is empty or contains no valid years.
    """
    first_year, last_year = limit_years()
    valid_years = []
    invalid_years = []

    if len(list_years) == 0:
        raise ValueError(
            f"The list is empty. Provide a list with years after {first_year} and before {last_year}.",  # noqa
        )

    for year in list_years:
        if not isinstance(year, int):
            invalid_years.append(year)
        elif first_year <= year <= last_year:
            valid_years.append(year)
        else:
            invalid_years.append(year)

    if len(valid_years) == 0:
        raise ValueError(
            f"The list is empty. Provide a list with years after {first_year} and before {last_year}.",  # noqa
        )

    if len(invalid_years) > 0:
        print(f"The elements {invalid_years} were removed from the list.")

    return valid_years

limit_years()

Calculate the valid year range for data collection.

Determines the earliest year from which data can be collected and the latest valid year based on the current date.

Returns

tuple[int, int] A tuple containing two integers: - The first integer is the earliest year from which data collection is valid. - The second integer is the latest valid year for data collection based on the current date.

Source code in app/tools/collectors.py 
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
def limit_years() -> tuple[int, int]:
    """Calculate the valid year range for data collection.

    Determines the earliest year from which data can be collected and the
    latest valid year based on the current date.

    Returns
    -------
    tuple[int, int]
        A tuple containing two integers:
        - The first integer is the earliest year from which data collection
        is valid.
        - The second integer is the latest valid year for data collection
        based on the current date.
    """
    FIRST_YEAR_WITH_DATA = 2000
    current_day = datetime.now().day
    last_year_month = datetime.today() - timedelta(current_day + 1)
    last_valid_year = last_year_month.year

    return FIRST_YEAR_WITH_DATA, last_valid_year