csv-insights 1.0.0__tar.gz

csv_insights-1.0.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Smriti12182004
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

csv_insights-1.0.0/PKG-INFO

@@ -0,0 +1,45 @@
+Metadata-Version: 2.4
+Name: csv-insights
+Version: 1.0.0
+Summary: A Python package for CSV profiling, data analysis, and statistical summaries
+Author: Smriti
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+# csvstat-package
+
+A lightweight Python package for **CSV profiling and data analysis**.  
+`csvstat` helps users quickly understand the structure and content of CSV files by generating useful statistics, detecting data types, and identifying missing values.
+
+## Features
+
+- 📊 **CSV File Profiling**
+  - Analyze CSV files and generate a structured summary
+  - Get total number of rows and columns
+
+- 🔍 **Column Analysis**
+  - Automatically detect column data types:
+    - Numeric columns
+    - Text columns
+  - Identify missing values in each column
+
+- 📈 **Numeric Statistics**
+  - Calculate statistical summaries for numeric columns:
+    - Minimum value
+    - Maximum value
+    - Mean value
+
+- 🔤 **Text Analysis**
+  - Find the most frequent values in text columns
+  - Generate top occurring values with their frequency
+
+- 💻 **Command Line Interface**
+  - Analyze CSV files directly from the terminal using the `csvstat` command
+
+## Installation
+
+Install `csvstat-package` from PyPI:
+
+```bash
+pip install csvstat-package

csv_insights-1.0.0/README.md

@@ -0,0 +1,36 @@
+# csvstat-package
+
+A lightweight Python package for **CSV profiling and data analysis**.  
+`csvstat` helps users quickly understand the structure and content of CSV files by generating useful statistics, detecting data types, and identifying missing values.
+
+## Features
+
+- 📊 **CSV File Profiling**
+  - Analyze CSV files and generate a structured summary
+  - Get total number of rows and columns
+
+- 🔍 **Column Analysis**
+  - Automatically detect column data types:
+    - Numeric columns
+    - Text columns
+  - Identify missing values in each column
+
+- 📈 **Numeric Statistics**
+  - Calculate statistical summaries for numeric columns:
+    - Minimum value
+    - Maximum value
+    - Mean value
+
+- 🔤 **Text Analysis**
+  - Find the most frequent values in text columns
+  - Generate top occurring values with their frequency
+
+- 💻 **Command Line Interface**
+  - Analyze CSV files directly from the terminal using the `csvstat` command
+
+## Installation
+
+Install `csvstat-package` from PyPI:
+
+```bash
+pip install csvstat-package

csv_insights-1.0.0/csv_insights.egg-info/PKG-INFO

@@ -0,0 +1,45 @@
+Metadata-Version: 2.4
+Name: csv-insights
+Version: 1.0.0
+Summary: A Python package for CSV profiling, data analysis, and statistical summaries
+Author: Smriti
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+# csvstat-package
+
+A lightweight Python package for **CSV profiling and data analysis**.  
+`csvstat` helps users quickly understand the structure and content of CSV files by generating useful statistics, detecting data types, and identifying missing values.
+
+## Features
+
+- 📊 **CSV File Profiling**
+  - Analyze CSV files and generate a structured summary
+  - Get total number of rows and columns
+
+- 🔍 **Column Analysis**
+  - Automatically detect column data types:
+    - Numeric columns
+    - Text columns
+  - Identify missing values in each column
+
+- 📈 **Numeric Statistics**
+  - Calculate statistical summaries for numeric columns:
+    - Minimum value
+    - Maximum value
+    - Mean value
+
+- 🔤 **Text Analysis**
+  - Find the most frequent values in text columns
+  - Generate top occurring values with their frequency
+
+- 💻 **Command Line Interface**
+  - Analyze CSV files directly from the terminal using the `csvstat` command
+
+## Installation
+
+Install `csvstat-package` from PyPI:
+
+```bash
+pip install csvstat-package

csv_insights-1.0.0/csv_insights.egg-info/SOURCES.txt

@@ -0,0 +1,12 @@
+LICENSE
+README.md
+pyproject.toml
+csv_insights.egg-info/PKG-INFO
+csv_insights.egg-info/SOURCES.txt
+csv_insights.egg-info/dependency_links.txt
+csv_insights.egg-info/entry_points.txt
+csv_insights.egg-info/top_level.txt
+csvstat/__init__.py
+csvstat/analyzer.py
+csvstat/cli.py
+tests/test_analyzer.py

csv_insights-1.0.0/csv_insights.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

csv_insights-1.0.0/csv_insights.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+csvstat = csvstat.cli:main

csv_insights-1.0.0/csv_insights.egg-info/top_level.txt

@@ -0,0 +1 @@
+csvstat

csv_insights-1.0.0/csvstat/__init__.py

@@ -0,0 +1 @@
+from .analyzer import analyze_csv

csv_insights-1.0.0/csvstat/analyzer.py

@@ -0,0 +1,73 @@
+import csv
+from collections import Counter
+
+
+def analyze_csv(file_path, top=5):
+
+    with open(file_path, "r") as file:
+        reader = csv.reader(file)
+        data = list(reader)
+
+    headers = [header.strip() for header in data[0]]
+    rows = data[1:]
+
+    result = {
+        "rows": len(rows),
+        "columns": len(headers),
+        "column_details": {}
+    }
+
+    for i, column in enumerate(headers):
+
+        values = [
+            row[i].strip()
+            for row in rows
+        ]
+
+        missing = sum(
+            1 for value in values
+            if value == ""
+        )
+
+        non_missing = [
+            value for value in values
+            if value != ""
+        ]
+
+        is_numeric = True
+
+        for value in non_missing:
+            try:
+                float(value)
+            except ValueError:
+                is_numeric = False
+                break
+
+        if is_numeric and non_missing:
+            data_type = "numeric"
+        else:
+            data_type = "text"
+
+        details = {
+            "type": data_type,
+            "missing": missing
+        }
+
+        if data_type == "numeric":
+
+            numeric_values = [
+                float(value)
+                for value in non_missing
+            ]
+
+            details["min"] = min(numeric_values)
+            details["mean"] = sum(numeric_values) / len(numeric_values)
+            details["max"] = max(numeric_values)
+
+        else:
+            counts = Counter(non_missing)
+            details["top_values"] = counts.most_common(top)
+
+        result["column_details"][column] = details
+
+    return result

csv_insights-1.0.0/csvstat/cli.py

@@ -0,0 +1,25 @@
+import argparse
+from .analyzer import analyze_csv
+
+
+def main():
+
+    parser = argparse.ArgumentParser(
+        description="CSV profiling tool"
+    )
+
+    parser.add_argument(
+        "file",
+        help="Path to CSV file"
+    )
+
+    args = parser.parse_args()
+
+    result = analyze_csv(args.file)
+
+    print("Rows:", result["rows"])
+    print("Columns:", result["columns"])
+
+
+if __name__ == "__main__":
+    main()

csv_insights-1.0.0/pyproject.toml

@@ -0,0 +1,24 @@
+[build-system]
+requires = ["setuptools>=61"]
+build-backend = "setuptools.build_meta"
+
+
+[project]
+name = "csv-insights"
+version = "1.0.0"
+description = "A Python package for CSV profiling, data analysis, and statistical summaries"
+readme = "README.md"
+
+authors = [
+    {name = "Smriti"}
+]
+
+dependencies = []
+
+
+[project.scripts]
+csvstat = "csvstat.cli:main"
+
+
+[tool.setuptools.packages.find]
+include = ["csvstat*"]

csv_insights-1.0.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

csv_insights-1.0.0/tests/test_analyzer.py

@@ -0,0 +1,127 @@
+import pytest
+from csvstat import analyze_csv
+
+
+@pytest.fixture
+def csv_result():
+    result = analyze_csv("data/sample.csv")
+    return result
+
+
+def test_row_count(csv_result):
+    assert csv_result["rows"] == 4
+
+
+def test_column_count(csv_result):
+    assert csv_result["columns"] == 2
+
+
+def test_numeric_column_detection(csv_result):
+    assert csv_result["column_details"]["Age"]["type"] == "numeric"
+
+
+def test_text_column_detection(csv_result):
+    assert csv_result["column_details"]["Name"]["type"] == "text"
+
+
+def test_missing_values(csv_result):
+    assert csv_result["column_details"]["Age"]["missing"] == 0
+
+
+def test_numeric_statistics(csv_result):
+    age_details = csv_result["column_details"]["Age"]
+
+    assert age_details["min"] == 25
+    assert age_details["max"] == 35
+
+
+# New test cases
+
+def test_numeric_mean(csv_result):
+    age_details = csv_result["column_details"]["Age"]
+
+    assert age_details["mean"] == 29.5
+
+
+def test_text_top_values(csv_result):
+    name_details = csv_result["column_details"]["Name"]
+
+    assert "top_values" in name_details
+    assert len(name_details["top_values"]) > 0
+
+
+def test_column_details_exist(csv_result):
+    assert "Name" in csv_result["column_details"]
+    assert "Age" in csv_result["column_details"]
+
+
+def test_result_structure(csv_result):
+    assert "rows" in csv_result
+    assert "columns" in csv_result
+    assert "column_details" in csv_result
+
+
+def test_numeric_min_less_than_max(csv_result):
+    age_details = csv_result["column_details"]["Age"]
+
+    assert age_details["min"] < age_details["max"]
+
+
+def test_numeric_values_are_correct_type(csv_result):
+    age_details = csv_result["column_details"]["Age"]
+
+    assert isinstance(age_details["min"], float)
+    assert isinstance(age_details["max"], float)
+
+def test_default_top_values_limit(csv_result):
+    name_details = csv_result["column_details"]["Name"]
+
+    assert len(name_details["top_values"]) <= 5
+
+
+def test_rows_value_is_integer(csv_result):
+    assert isinstance(csv_result["rows"], int)
+
+
+def test_columns_value_is_integer(csv_result):
+    assert isinstance(csv_result["columns"], int)
+
+
+def test_column_details_is_dictionary(csv_result):
+    assert isinstance(csv_result["column_details"], dict)
+
+
+def test_age_details_contains_required_fields(csv_result):
+    age_details = csv_result["column_details"]["Age"]
+
+    assert "type" in age_details
+    assert "missing" in age_details
+    assert "min" in age_details
+    assert "max" in age_details
+    assert "mean" in age_details
+
+
+def test_name_details_contains_required_fields(csv_result):
+    name_details = csv_result["column_details"]["Name"]
+
+    assert "type" in name_details
+    assert "missing" in name_details
+    assert "top_values" in name_details
+
+
+def test_no_missing_values_in_name(csv_result):
+    assert csv_result["column_details"]["Name"]["missing"] == 0
+
+
+def test_numeric_mean_between_min_max(csv_result):
+    age_details = csv_result["column_details"]["Age"]
+
+    assert age_details["min"] <= age_details["mean"] <= age_details["max"]
+
+
+def test_age_type_not_text(csv_result):
+    assert csv_result["column_details"]["Age"]["type"] != "text"
+
+
+def test_name_type_not_numeric(csv_result):
+    assert csv_result["column_details"]["Name"]["type"] != "numeric"