iragi 0.1.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
iragi/__init__.py ADDED
@@ -0,0 +1,14 @@
1
+ """Iragi: Modular File Inspection, Extraction, and Analytics Toolkit.
2
+
3
+ Unifies Scan, PDF, and orchestration pipelines for reliable data quality workflows.
4
+
5
+ Example:
6
+ >>> import iragi
7
+ >>> print(iragi.__version__)
8
+ '0.1.0'
9
+ """
10
+
11
+ from iragi.scan import scan, scan_dataframe
12
+
13
+ __version__ = "0.1.0"
14
+ __all__ = ["__version__", "scan", "scan_dataframe"]
iragi/core/config.py ADDED
@@ -0,0 +1,59 @@
1
+ """Configuration management for Iragi.
2
+
3
+ Provides system-wide defaults, tunable quality weights, and persistent settings.
4
+
5
+ Example:
6
+ >>> from iragi.core.config import IragiConfig
7
+ >>> config = IragiConfig()
8
+ >>> config.outlier_iqr_multiplier
9
+ 1.5
10
+ """
11
+
12
+ import os
13
+ from dataclasses import dataclass
14
+ from pathlib import Path
15
+
16
+
17
+ @dataclass
18
+ class IragiConfig:
19
+ """Runtime configuration options for Iragi analyses.
20
+
21
+ :param missing_penalty_weight: Weight deducted for missing cells ratio.
22
+ :type missing_penalty_weight: float
23
+ :param duplicate_penalty_weight: Weight deducted for duplicate rows ratio.
24
+ :type duplicate_penalty_weight: float
25
+ :param outlier_penalty_weight: Weight deducted for numerical outlier ratio.
26
+ :type outlier_penalty_weight: float
27
+ :param invalid_date_penalty_weight: Weight deducted for unparseable dates.
28
+ :type invalid_date_penalty_weight: float
29
+ :param outlier_iqr_multiplier: IQR multiplier used to detect statistical outliers.
30
+ :type outlier_iqr_multiplier: float
31
+ :param db_path: Path to the local SQLite history database.
32
+ :type db_path: Path
33
+
34
+ Example:
35
+ >>> cfg = IragiConfig(outlier_iqr_multiplier=2.0)
36
+ >>> cfg.outlier_iqr_multiplier
37
+ 2.0
38
+ """
39
+
40
+ missing_penalty_weight: float = 35.0
41
+ duplicate_penalty_weight: float = 25.0
42
+ outlier_penalty_weight: float = 20.0
43
+ invalid_date_penalty_weight: float = 20.0
44
+ outlier_iqr_multiplier: float = 1.5
45
+ db_path: Path = Path(os.environ.get("IRAGI_DB_PATH", Path.home() / ".iragi" / "history.db"))
46
+
47
+
48
+ def get_default_config() -> IragiConfig:
49
+ """Retrieve the standard system default configuration.
50
+
51
+ :return: An initialized default IragiConfig instance.
52
+ :rtype: IragiConfig
53
+
54
+ Example:
55
+ >>> cfg = get_default_config()
56
+ >>> isinstance(cfg, IragiConfig)
57
+ True
58
+ """
59
+ return IragiConfig()
@@ -0,0 +1,67 @@
1
+ """Core exceptions for Iragi.
2
+
3
+ This module defines domain-specific exceptions used across inspection,
4
+ cleaning, parsing, and reporting subsystems.
5
+
6
+ Example:
7
+ >>> from iragi.core.exceptions import IragiDataError
8
+ >>> raise IragiDataError("Invalid tabular data format")
9
+ Traceback (most recent call last):
10
+ ...
11
+ iragi.core.exceptions.IragiDataError: Invalid tabular data format
12
+ """
13
+
14
+
15
+ class IragiError(Exception):
16
+ """Base exception for all Iragi errors.
17
+
18
+ Example:
19
+ >>> err = IragiError("Something failed")
20
+ >>> str(err)
21
+ 'Something failed'
22
+ """
23
+ pass
24
+
25
+
26
+ class IragiDataError(IragiError):
27
+ """Raised when data inspection or cleaning fails.
28
+
29
+ Example:
30
+ >>> err = IragiDataError("Unsupported file type")
31
+ >>> str(err)
32
+ 'Unsupported file type'
33
+ """
34
+ pass
35
+
36
+
37
+ class IragiLogError(IragiError):
38
+ """Raised when log parsing or analysis encounters an invalid state.
39
+
40
+ Example:
41
+ >>> err = IragiLogError("Failed to parse log line")
42
+ >>> str(err)
43
+ 'Failed to parse log line'
44
+ """
45
+ pass
46
+
47
+
48
+ class IragiConfigError(IragiError):
49
+ """Raised when configuration values are missing or invalid.
50
+
51
+ Example:
52
+ >>> err = IragiConfigError("Invalid scoring threshold")
53
+ >>> str(err)
54
+ 'Invalid scoring threshold'
55
+ """
56
+ pass
57
+
58
+
59
+ class IragiReportError(IragiError):
60
+ """Raised when generating a report fails.
61
+
62
+ Example:
63
+ >>> err = IragiReportError("Template rendering failed")
64
+ >>> str(err)
65
+ 'Template rendering failed'
66
+ """
67
+ pass
iragi/core/models.py ADDED
@@ -0,0 +1,201 @@
1
+ """Core domain models for Iragi.
2
+
3
+ Provides structured representations for tabular inspection results,
4
+ individual column profiles, log analysis summaries, and quality metrics.
5
+
6
+ Example:
7
+ >>> from iragi.core.models import QualityScore, DataInspectionResult
8
+ >>> score = QualityScore(total_score=85.5, breakdown={"missing_penalty": 10.0})
9
+ >>> score.total_score
10
+ 85.5
11
+ """
12
+
13
+ from dataclasses import dataclass, field
14
+ from datetime import datetime
15
+ from typing import Any, Dict, List, Optional
16
+
17
+
18
+ @dataclass
19
+ class QualityScore:
20
+ """Represents an explainable data quality score.
21
+
22
+ :param total_score: The final computed quality score between 0 and 100.
23
+ :type total_score: float
24
+ :param breakdown: Penalty and bonus components contributing to the score.
25
+ :type breakdown: Dict[str, float]
26
+ :param explanations: Human-readable explanations for applied deductions.
27
+ :type explanations: List[str]
28
+
29
+ Example:
30
+ >>> qs = QualityScore(total_score=90.0, breakdown={"missing": -10.0}, explanations=["10% missing rows"])
31
+ >>> qs.total_score
32
+ 90.0
33
+ """
34
+
35
+ total_score: float
36
+ breakdown: Dict[str, float] = field(default_factory=dict)
37
+ explanations: List[str] = field(default_factory=list)
38
+
39
+
40
+ @dataclass
41
+ class ColumnProfile:
42
+ """Detailed profile metrics for a single tabular column.
43
+
44
+ :param name: Column header name.
45
+ :type name: str
46
+ :param inferred_type: Inferred data type (e.g. numeric, datetime, categorical).
47
+ :type inferred_type: str
48
+ :param total_count: Total number of values processed.
49
+ :type total_count: int
50
+ :param missing_count: Number of missing/null values.
51
+ :type missing_count: int
52
+ :param unique_count: Number of unique distinct values.
53
+ :type unique_count: int
54
+ :param invalid_dates_count: Count of unparseable date strings if column is date-like.
55
+ :type invalid_dates_count: int
56
+ :param outliers_count: Count of potential numerical outliers detected.
57
+ :type outliers_count: int
58
+ :param summary_stats: Descriptive numerical or categorical summary statistics.
59
+ :type summary_stats: Dict[str, Any]
60
+
61
+ Example:
62
+ >>> col = ColumnProfile("age", "numeric", 100, 5, 45, 0, 2, {"mean": 32.4})
63
+ >>> col.name
64
+ 'age'
65
+ """
66
+
67
+ name: str
68
+ inferred_type: str
69
+ total_count: int
70
+ missing_count: int
71
+ unique_count: int
72
+ invalid_dates_count: int = 0
73
+ outliers_count: int = 0
74
+ summary_stats: Dict[str, Any] = field(default_factory=dict)
75
+
76
+
77
+ @dataclass
78
+ class DataInspectionResult:
79
+ """Consolidated findings from tabular data inspection.
80
+
81
+ :param file_path: Source path of the analyzed file.
82
+ :type file_path: str
83
+ :param row_count: Total row count in tabular dataset.
84
+ :type row_count: int
85
+ :param column_count: Total column count.
86
+ :type column_count: int
87
+ :param missing_values_count: Aggregated count of missing cells.
88
+ :type missing_values_count: int
89
+ :param duplicate_rows_count: Number of duplicate rows detected.
90
+ :type duplicate_rows_count: int
91
+ :param invalid_dates_count: Total invalid date formats encountered.
92
+ :type invalid_dates_count: int
93
+ :param potential_outliers_count: Total potential statistical outliers.
94
+ :type potential_outliers_count: int
95
+ :param quality_score: Computed quality score with breakdown.
96
+ :type quality_score: QualityScore
97
+ :param column_profiles: Detailed profiles per column.
98
+ :type column_profiles: List[ColumnProfile]
99
+ :param recommendations: Actionable cleaning and quality improvement recommendations.
100
+ :type recommendations: List[str]
101
+ :param analyzed_at: Timestamp of inspection completion.
102
+ :type analyzed_at: datetime
103
+
104
+ Example:
105
+ >>> score = QualityScore(total_score=95.0)
106
+ >>> res = DataInspectionResult("data.csv", 100, 3, 2, 0, 0, 1, score)
107
+ >>> res.row_count
108
+ 100
109
+ """
110
+
111
+ file_path: str
112
+ row_count: int
113
+ column_count: int
114
+ missing_values_count: int
115
+ duplicate_rows_count: int
116
+ invalid_dates_count: int
117
+ potential_outliers_count: int
118
+ quality_score: QualityScore
119
+ column_profiles: List[ColumnProfile] = field(default_factory=list)
120
+ recommendations: List[str] = field(default_factory=list)
121
+ analyzed_at: datetime = field(default_factory=datetime.now)
122
+
123
+
124
+ @dataclass
125
+ class LogEntry:
126
+ """Structured representation of a parsed log record.
127
+
128
+ :param raw: Original unmodified raw log line.
129
+ :type raw: str
130
+ :param timestamp: Parsed timestamp if available.
131
+ :type timestamp: Optional[datetime]
132
+ :param level: Log level (e.g. INFO, WARN, ERROR, CRITICAL).
133
+ :type level: str
134
+ :param message: Extracted log message or request payload.
135
+ :type message: str
136
+ :param status_code: HTTP status code if present in the line.
137
+ :type status_code: Optional[int]
138
+ :param ip_address: Client IP address if present.
139
+ :type ip_address: Optional[str]
140
+ :param source: Originating parser or format identifier (e.g. nginx, django).
141
+ :type source: str
142
+
143
+ Example:
144
+ >>> entry = LogEntry("line 1", None, "ERROR", "Failed db connection", None, None, "django")
145
+ >>> entry.level
146
+ 'ERROR'
147
+ """
148
+
149
+ raw: str
150
+ timestamp: Optional[datetime]
151
+ level: str
152
+ message: str
153
+ status_code: Optional[int] = None
154
+ ip_address: Optional[str] = None
155
+ source: str = "generic"
156
+
157
+
158
+ @dataclass
159
+ class LogAnalysisResult:
160
+ """Consolidated output from technical log inspection.
161
+
162
+ :param file_path: Path of the inspected log file.
163
+ :type file_path: str
164
+ :param total_lines: Total lines processed.
165
+ :type total_lines: int
166
+ :param parsed_lines: Number of successfully parsed log lines.
167
+ :type parsed_lines: int
168
+ :param unparsed_lines: Number of lines failing parser structure.
169
+ :type unparsed_lines: int
170
+ :param level_counts: Distribution of records by log level.
171
+ :type level_counts: Dict[str, int]
172
+ :param http_status_counts: Distribution of HTTP response status codes.
173
+ :type http_status_counts: Dict[int, int]
174
+ :param top_errors: Frequently repeated error messages and their occurrence counts.
175
+ :type top_errors: List[Dict[str, Any]]
176
+ :param unique_ips: List of distinct anonymized or extracted IP addresses.
177
+ :type unique_ips: List[str]
178
+ :param peak_error_periods: Time windows exhibiting highest error densities.
179
+ :type peak_error_periods: List[Dict[str, Any]]
180
+ :param recommendations: Diagnostics summary and operational tips.
181
+ :type recommendations: List[str]
182
+ :param analyzed_at: Timestamp of inspection.
183
+ :type analyzed_at: datetime
184
+
185
+ Example:
186
+ >>> res = LogAnalysisResult("app.log", 100, 98, 2, {"ERROR": 5}, {500: 2}, [], [], [])
187
+ >>> res.total_lines
188
+ 100
189
+ """
190
+
191
+ file_path: str
192
+ total_lines: int
193
+ parsed_lines: int
194
+ unparsed_lines: int
195
+ level_counts: Dict[str, int] = field(default_factory=dict)
196
+ http_status_counts: Dict[int, int] = field(default_factory=dict)
197
+ top_errors: List[Dict[str, Any]] = field(default_factory=list)
198
+ unique_ips: List[str] = field(default_factory=list)
199
+ peak_error_periods: List[Dict[str, Any]] = field(default_factory=list)
200
+ recommendations: List[str] = field(default_factory=list)
201
+ analyzed_at: datetime = field(default_factory=datetime.now)
iragi/scan/__init__.py ADDED
@@ -0,0 +1,36 @@
1
+ """Iragi Scan engine: Tabular data inspection, profiling, and quality auditing.
2
+
3
+ Provides tools for inspecting CSV, Excel, and JSON files, computing column
4
+ distributions, identifying anomalies, and calculating explainable quality scores.
5
+
6
+ Example:
7
+ >>> from iragi import scan
8
+ >>> import tempfile
9
+ >>> tmp = tempfile.NamedTemporaryFile(mode='w', suffix='.csv', delete=False)
10
+ >>> _ = tmp.write("col_a,col_b\\n1,2\\n3,4")
11
+ >>> tmp.close()
12
+ >>> res = scan(tmp.name)
13
+ >>> res.quality_score.total_score
14
+ 100.0
15
+ """
16
+
17
+ from iragi.scan.engine import scan, scan_dataframe, compute_quality_score, generate_recommendations
18
+ from iragi.scan.readers import load_tabular_file, read_csv_file, read_excel_file, read_json_file
19
+ from iragi.scan.profiler import profile_dataframe, infer_column_type, detect_outliers_iqr
20
+ from iragi.scan.reports import to_json_report, inspection_result_to_dict
21
+
22
+ __all__ = [
23
+ "scan",
24
+ "scan_dataframe",
25
+ "compute_quality_score",
26
+ "generate_recommendations",
27
+ "load_tabular_file",
28
+ "read_csv_file",
29
+ "read_excel_file",
30
+ "read_json_file",
31
+ "profile_dataframe",
32
+ "infer_column_type",
33
+ "detect_outliers_iqr",
34
+ "to_json_report",
35
+ "inspection_result_to_dict",
36
+ ]
iragi/scan/engine.py ADDED
@@ -0,0 +1,241 @@
1
+ """Core execution engine for Iragi Scan.
2
+
3
+ Coordinates file loading, column profiling, explainable quality scoring,
4
+ and actionable cleaning recommendations.
5
+
6
+ Example:
7
+ >>> from iragi.scan.engine import scan
8
+ >>> import tempfile
9
+ >>> tmp = tempfile.NamedTemporaryFile(mode='w', suffix='.csv', delete=False)
10
+ >>> _ = tmp.write("name,score\\nAlice,95\\nBob,80")
11
+ >>> tmp.close()
12
+ >>> res = scan(tmp.name)
13
+ >>> res.quality_score.total_score >= 90.0
14
+ True
15
+ """
16
+
17
+ from pathlib import Path
18
+ from typing import List, Tuple, Union, Optional
19
+ from datetime import datetime
20
+ import pandas as pd
21
+ from iragi.core.config import IragiConfig, get_default_config
22
+ from iragi.core.models import QualityScore, DataInspectionResult
23
+ from iragi.scan.readers import load_tabular_file
24
+ from iragi.scan.profiler import profile_dataframe
25
+
26
+
27
+ def compute_quality_score(
28
+ row_count: int,
29
+ column_count: int,
30
+ missing_count: int,
31
+ duplicate_rows: int,
32
+ outliers_count: int,
33
+ invalid_dates_count: int,
34
+ config: IragiConfig,
35
+ ) -> QualityScore:
36
+ """Calculate an explainable data quality score on a 0-100 scale.
37
+
38
+ :param row_count: Number of rows in dataset.
39
+ :type row_count: int
40
+ :param column_count: Number of columns.
41
+ :type column_count: int
42
+ :param missing_count: Total missing cell values.
43
+ :type missing_count: int
44
+ :param duplicate_rows: Number of duplicated rows.
45
+ :type duplicate_rows: int
46
+ :param outliers_count: Total potential statistical outliers.
47
+ :type outliers_count: int
48
+ :param invalid_dates_count: Total invalid date formats.
49
+ :type invalid_dates_count: int
50
+ :param config: Runtime scoring weights configuration.
51
+ :type config: IragiConfig
52
+ :return: QualityScore instance with exact deduction breakdown.
53
+ :rtype: QualityScore
54
+
55
+ Example:
56
+ >>> from iragi.core.config import get_default_config
57
+ >>> qs = compute_quality_score(100, 5, 0, 0, 0, 0, get_default_config())
58
+ >>> qs.total_score
59
+ 100.0
60
+ """
61
+ if row_count == 0 or column_count == 0:
62
+ return QualityScore(
63
+ total_score=0.0,
64
+ breakdown={"empty_dataset": 100.0},
65
+ explanations=["Dataset contains zero rows or zero columns."],
66
+ )
67
+
68
+ total_cells = row_count * column_count
69
+ missing_ratio = missing_count / total_cells if total_cells > 0 else 0.0
70
+ duplicate_ratio = duplicate_rows / row_count if row_count > 0 else 0.0
71
+ outlier_ratio = min(1.0, outliers_count / row_count) if row_count > 0 else 0.0
72
+ invalid_date_ratio = min(1.0, invalid_dates_count / row_count) if row_count > 0 else 0.0
73
+
74
+ missing_penalty = round(missing_ratio * config.missing_penalty_weight, 2)
75
+ duplicate_penalty = round(duplicate_ratio * config.duplicate_penalty_weight, 2)
76
+ outlier_penalty = round(outlier_ratio * config.outlier_penalty_weight, 2)
77
+ invalid_date_penalty = round(invalid_date_ratio * config.invalid_date_penalty_weight, 2)
78
+
79
+ total_deductions = missing_penalty + duplicate_penalty + outlier_penalty + invalid_date_penalty
80
+ final_score = max(0.0, round(100.0 - total_deductions, 2))
81
+
82
+ breakdown = {
83
+ "missing_penalty": missing_penalty,
84
+ "duplicate_penalty": duplicate_penalty,
85
+ "outlier_penalty": outlier_penalty,
86
+ "invalid_date_penalty": invalid_date_penalty,
87
+ }
88
+
89
+ explanations: List[str] = []
90
+ if missing_penalty > 0:
91
+ explanations.append(f"Missing values deducted {missing_penalty} pts ({missing_count} null cells).")
92
+ if duplicate_penalty > 0:
93
+ explanations.append(f"Duplicate rows deducted {duplicate_penalty} pts ({duplicate_rows} duplicate rows).")
94
+ if outlier_penalty > 0:
95
+ explanations.append(f"Outliers deducted {outlier_penalty} pts ({outliers_count} extreme values).")
96
+ if invalid_date_penalty > 0:
97
+ explanations.append(f"Invalid dates deducted {invalid_date_penalty} pts ({invalid_dates_count} invalid entries).")
98
+
99
+ if not explanations:
100
+ explanations.append("Excellent data hygiene: zero missing, duplicate, or outlier entries detected.")
101
+
102
+ return QualityScore(total_score=final_score, breakdown=breakdown, explanations=explanations)
103
+
104
+
105
+ def generate_recommendations(
106
+ missing_count: int,
107
+ duplicate_rows: int,
108
+ outliers_count: int,
109
+ invalid_dates_count: int,
110
+ ) -> List[str]:
111
+ """Generate prioritized, actionable cleaning recommendations.
112
+
113
+ :param missing_count: Total missing cell values.
114
+ :type missing_count: int
115
+ :param duplicate_rows: Number of duplicated rows.
116
+ :type duplicate_rows: int
117
+ :param outliers_count: Total potential statistical outliers.
118
+ :type outliers_count: int
119
+ :param invalid_dates_count: Total invalid date formats.
120
+ :type invalid_dates_count: int
121
+ :return: List of recommended cleaning operations.
122
+ :rtype: List[str]
123
+
124
+ Example:
125
+ >>> recs = generate_recommendations(10, 2, 0, 0)
126
+ >>> len(recs)
127
+ 2
128
+ """
129
+ recommendations: List[str] = []
130
+
131
+ if duplicate_rows > 0:
132
+ recommendations.append(
133
+ f"Deduplicate dataset: {duplicate_rows} identical rows detected. Apply row deduplication."
134
+ )
135
+
136
+ if missing_count > 0:
137
+ recommendations.append(
138
+ f"Handle missing values: {missing_count} null cells found. Consider imputation (mean/median) or dropping empty records."
139
+ )
140
+
141
+ if invalid_dates_count > 0:
142
+ recommendations.append(
143
+ f"Standardize date formats: {invalid_dates_count} date strings could not be parsed to ISO standard."
144
+ )
145
+
146
+ if outliers_count > 0:
147
+ recommendations.append(
148
+ f"Audit statistical outliers: {outliers_count} numerical values exceed 1.5x IQR boundaries."
149
+ )
150
+
151
+ if not recommendations:
152
+ recommendations.append("Dataset passes all quality checks. No immediate cleaning actions required.")
153
+
154
+ return recommendations
155
+
156
+
157
+ def scan_dataframe(
158
+ df: pd.DataFrame,
159
+ source_name: str = "in_memory_dataframe",
160
+ config: Optional[IragiConfig] = None,
161
+ ) -> DataInspectionResult:
162
+ """Inspect and profile an in-memory pandas DataFrame.
163
+
164
+ :param df: Target pandas DataFrame.
165
+ :type df: pd.DataFrame
166
+ :param source_name: Identifier for the data source.
167
+ :type source_name: str
168
+ :param config: Optional custom configuration instance.
169
+ :type config: Optional[IragiConfig]
170
+ :return: Comprehensive DataInspectionResult.
171
+ :rtype: DataInspectionResult
172
+
173
+ Example:
174
+ >>> import pandas as pd
175
+ >>> df = pd.DataFrame({"col1": [1, 2, 3]})
176
+ >>> res = scan_dataframe(df)
177
+ >>> res.column_count
178
+ 1
179
+ """
180
+ cfg = config or get_default_config()
181
+
182
+ row_count = int(df.shape[0])
183
+ column_count = int(df.shape[1])
184
+ missing_values_count = int(df.isna().sum().sum())
185
+
186
+ column_profiles, duplicate_rows, outliers_count, invalid_dates = profile_dataframe(df, config=cfg)
187
+
188
+ quality_score = compute_quality_score(
189
+ row_count=row_count,
190
+ column_count=column_count,
191
+ missing_count=missing_values_count,
192
+ duplicate_rows=duplicate_rows,
193
+ outliers_count=outliers_count,
194
+ invalid_dates_count=invalid_dates,
195
+ config=cfg,
196
+ )
197
+
198
+ recommendations = generate_recommendations(
199
+ missing_count=missing_values_count,
200
+ duplicate_rows=duplicate_rows,
201
+ outliers_count=outliers_count,
202
+ invalid_dates_count=invalid_dates,
203
+ )
204
+
205
+ return DataInspectionResult(
206
+ file_path=source_name,
207
+ row_count=row_count,
208
+ column_count=column_count,
209
+ missing_values_count=missing_values_count,
210
+ duplicate_rows_count=duplicate_rows,
211
+ invalid_dates_count=invalid_dates,
212
+ potential_outliers_count=outliers_count,
213
+ quality_score=quality_score,
214
+ column_profiles=column_profiles,
215
+ recommendations=recommendations,
216
+ analyzed_at=datetime.now(),
217
+ )
218
+
219
+
220
+ def scan(file_path: Union[str, Path], config: Optional[IragiConfig] = None) -> DataInspectionResult:
221
+ """Inspect, profile, and evaluate the quality of a CSV, Excel, or JSON file.
222
+
223
+ :param file_path: Path to target file.
224
+ :type file_path: Union[str, Path]
225
+ :param config: Optional custom configuration instance.
226
+ :type config: Optional[IragiConfig]
227
+ :return: Comprehensive DataInspectionResult.
228
+ :rtype: DataInspectionResult
229
+
230
+ Example:
231
+ >>> import tempfile
232
+ >>> tmp = tempfile.NamedTemporaryFile(mode='w', suffix='.csv', delete=False)
233
+ >>> _ = tmp.write("id,value\\n1,100\\n2,200")
234
+ >>> tmp.close()
235
+ >>> res = scan(tmp.name)
236
+ >>> res.row_count
237
+ 2
238
+ """
239
+ path = Path(file_path)
240
+ df, _ = load_tabular_file(path)
241
+ return scan_dataframe(df, source_name=str(path), config=config)