data-advisor 0.1.0__py3-none-any.whl

data_advisor/visualizer.py

@@ -0,0 +1,236 @@
+"""
+visualizer.py - Generates beautiful, publication-ready Matplotlib & Seaborn visualization code.
+
+Specifically crafted to produce exam-winning EDA charts that immediately prove hypotheses
+and illustrate data distributions.
+"""
+
+from __future__ import annotations
+
+from typing import Any, Dict, List, Optional
+
+
+class VisualizationAdvisor:
+    """
+    Constructs executable Matplotlib and Seaborn code blocks tailored to
+    the dataset's detected variable types and target relationships.
+    """
+
+    def __init__(self, scan_results: Dict[str, Any]) -> None:
+        self.scan = scan_results
+        self.distributions = scan_results.get("distributions", {})
+        self.categoricals = scan_results.get("categoricals", {})
+        self.target = scan_results.get("target")
+        self.dtypes = scan_results.get("data_types", {})
+
+    # -------------------------------------------------------------------------
+    # 1. Univariate Code Generation
+    # -------------------------------------------------------------------------
+    def generate_univariate_code(self) -> str:
+        """Generate code for numeric distribution histograms and categorical countplots."""
+        excluded_cats = set(
+            list(self.dtypes.get("potential_dates", []))
+            + list(self.dtypes.get("potential_ids", []))
+            + list(self.dtypes.get("constant_columns", []))
+        )
+        num_cols = list(self.distributions.keys())[:6]  # Focus on top 6 to prevent plot clutter
+        cat_cols = [c for c in self.categoricals.keys() if c not in excluded_cats][:6]
+
+        code_lines = [
+            "# =============================================================================",
+            "# SECTION 1: UNIVARIATE DISTRIBUTION PLOTS (Matplotlib & Seaborn)",
+            "# =============================================================================",
+            "import matplotlib.pyplot as plt",
+            "import seaborn as sns",
+            "",
+            "# Set aesthetic style",
+            "sns.set_theme(style='whitegrid', palette='muted')",
+            "plt.rcParams.update({'font.sans-serif': 'Arial', 'font.size': 11})",
+            "",
+        ]
+
+        if num_cols:
+            code_lines.extend([
+                f"# Numeric Distributions: Histograms + Boxplots for {len(num_cols)} key features",
+                f"numeric_features = {repr(num_cols)}",
+                "for col in numeric_features:",
+                "    if col in df.columns:",
+                "        fig, (ax_box, ax_hist) = plt.subplots(",
+                "            nrows=2, sharex=True, gridspec_kw={'height_ratios': [0.2, 0.8]}, figsize=(8, 5)",
+                "        )",
+                "        # Outlier boxplot on top",
+                "        sns.boxplot(x=df[col], ax=ax_box, color='#4C72B0', fliersize=4)",
+                "        ax_box.set(xlabel='')",
+                "        ax_box.set_title(f'Distribution & Outliers: {col}', fontsize=12, fontweight='bold')",
+                "        # Density histogram with KDE on bottom",
+                "        sns.histplot(df[col], kde=True, ax=ax_hist, color='#4C72B0', bins=30)",
+                "        ax_hist.axvline(df[col].mean(), color='crimson', linestyle='--', linewidth=1.5, label='Mean')",
+                "        ax_hist.axvline(df[col].median(), color='darkgreen', linestyle='-', linewidth=1.5, label='Median')",
+                "        ax_hist.legend()",
+                "        plt.tight_layout()",
+                "        plt.show()",
+                "        plt.close('all')",
+                "",
+            ])
+
+        if cat_cols:
+            code_lines.extend([
+                f"# Categorical Distributions: Frequency Countplots for {len(cat_cols)} categories",
+                f"categorical_features = {repr(cat_cols)}",
+                "for col in categorical_features:",
+                "    if col in df.columns:",
+                "        plt.figure(figsize=(8, 4))",
+                "        order = df[col].value_counts().index[:10]  # Show top 10 categories",
+                "        ax = sns.countplot(data=df, x=col, order=order, color='#4C72B0')",
+                "        plt.title(f'Frequency Distribution: {col}', fontsize=12, fontweight='bold')",
+                "        plt.xticks(rotation=45, ha='right')",
+                "        # Annotate bar percentages",
+                "        total = len(df[col].dropna())",
+                "        for p in ax.patches:",
+                "            height = p.get_height()",
+                "            if height > 0:",
+                "                pct = f'{100 * height / total:.1f}%'",
+                "                ax.annotate(pct, (p.get_x() + p.get_width() / 2., height),",
+                "                            ha='center', va='bottom', fontsize=9, xytext=(0, 3), textcoords='offset points')",
+                "        plt.tight_layout()",
+                "        plt.show()",
+                "        plt.close('all')",
+                "",
+            ])
+
+        return "\n".join(code_lines)
+
+    # -------------------------------------------------------------------------
+    # 2. Correlation Matrix Heatmap Code
+    # -------------------------------------------------------------------------
+    def generate_correlation_code(self) -> str:
+        """Generate Seaborn correlation heatmap with upper-triangle masking."""
+        num_cols = list(self.distributions.keys())
+        if len(num_cols) < 2:
+            return "# Less than 2 numeric columns; correlation heatmap skipped.\n"
+
+        return "\n".join([
+            "# =============================================================================",
+            "# SECTION 2: CORRELATION MATRIX HEATMAP",
+            "# =============================================================================",
+            "import numpy as np",
+            "import matplotlib.pyplot as plt",
+            "import seaborn as sns",
+            "",
+            "plt.figure(figsize=(10, 8))",
+            "corr = df.select_dtypes(include=[np.number]).corr(method='pearson')",
+            "# Generate mask for the upper triangle",
+            "mask = np.triu(np.ones_like(corr, dtype=bool))",
+            "# Plot annotated diverging heatmap",
+            "sns.heatmap(",
+            "    corr, mask=mask, annot=True, fmt='.2f', cmap='vlag',",
+            "    vmin=-1.0, vmax=1.0, center=0, square=True, linewidths=0.5, cbar_kws={'shrink': 0.8}",
+            ")",
+            "plt.title('Feature Correlation Matrix (Pearson)', fontsize=14, fontweight='bold', pad=12)",
+            "plt.tight_layout()",
+            "plt.show()",
+            "",
+        ])
+
+    # -------------------------------------------------------------------------
+    # 3. Bivariate & Target-Specific Code
+    # -------------------------------------------------------------------------
+    def generate_target_plots_code(self) -> str:
+        """Generate targeted bivariate plots verifying relationships with the response variable."""
+        if not self.target:
+            return "# No target variable detected/specified for bivariate target visualizations.\n"
+
+        target_col = self.target.get("target_column")
+        prob_type = self.target.get("problem_type")
+        excluded_cats = set(
+            list(self.dtypes.get("potential_dates", []))
+            + list(self.dtypes.get("potential_ids", []))
+            + list(self.dtypes.get("constant_columns", []))
+        )
+        num_cols = [c for c in self.distributions.keys() if c != target_col][:4]
+        cat_cols = [c for c in self.categoricals.keys() if c != target_col and c not in excluded_cats][:3]
+
+        lines = [
+            "# =============================================================================",
+            f"# SECTION 3: BIVARIATE RELATIONSHIPS WITH TARGET: '{target_col}' ({prob_type.upper()})",
+            "# =============================================================================",
+            "import matplotlib.pyplot as plt",
+            "import seaborn as sns",
+            "",
+        ]
+
+        if prob_type == "regression":
+            # Target is continuous: Scatter plots with regression trends
+            lines.extend([
+                f"# Scatter Plots with Linear Regression Trendlines vs Target '{target_col}'",
+                f"top_numeric_features = {repr(num_cols)}",
+                "for col in top_numeric_features:",
+                "    if col in df.columns and TARGET in df.columns:",
+                "        plt.figure(figsize=(7, 4.5))",
+                f"        sns.regplot(data=df, x=col, y='{target_col}', scatter_kws={{'alpha': 0.4}}, line_kws={{'color': 'red'}})",
+                f"        plt.title(f'Relationship: {{col}} vs {target_col}', fontsize=12, fontweight='bold')",
+                "        plt.tight_layout()",
+                "        plt.show()",
+                "        plt.close('all')",
+                "",
+            ])
+            if cat_cols:
+                lines.extend([
+                    f"# Categorical Groups vs Continuous Target '{target_col}' (Boxplots)",
+                    f"key_cat_features = {repr(cat_cols)}",
+                    "for col in key_cat_features:",
+                    "    if col in df.columns and TARGET in df.columns:",
+                    "        plt.figure(figsize=(8, 4.5))",
+                    f"        sns.boxplot(data=df, x=col, y='{target_col}', palette='Set2')",
+                    f"        plt.title(f'{target_col} Distribution across {{col}} Levels', fontsize=12, fontweight='bold')",
+                    "        plt.xticks(rotation=30, ha='right')",
+                    "        plt.tight_layout()",
+                    "        plt.show()",
+                    "        plt.close('all')",
+                    "",
+                ])
+        else:
+            # Target is categorical: Boxplots/Violins grouped by target hue, and grouped countplots
+            lines.extend([
+                f"# Feature Distributions Conditioned on Target Classes '{target_col}'",
+                f"top_numeric_features = {repr(num_cols)}",
+                "for col in top_numeric_features:",
+                f"    if col in df.columns and '{target_col}' in df.columns:",
+                "        plt.figure(figsize=(7, 4.5))",
+                f"        sns.boxplot(data=df, x='{target_col}', y=col, color='#4C72B0')",
+                f"        plt.title(f'Distribution of {{col}} by {target_col}', fontsize=12, fontweight='bold')",
+                "        plt.tight_layout()",
+                "        plt.show()",
+                "        plt.close('all')",
+                "",
+            ])
+            if cat_cols:
+                lines.extend([
+                    f"# Categorical Contingency: Stacked/Grouped Countplots vs Target '{target_col}'",
+                    f"key_cat_features = {repr(cat_cols)}",
+                    "for col in key_cat_features:",
+                    f"    if col in df.columns and '{target_col}' in df.columns:",
+                    "        plt.figure(figsize=(8, 4.5))",
+                    f"        sns.countplot(data=df, x=col, hue='{target_col}', palette='Set1')",
+                    f"        plt.title(f'Contingency Distribution: {{col}} by {target_col}', fontsize=12, fontweight='bold')",
+                    "        plt.xticks(rotation=30, ha='right')",
+                    "        plt.legend(title='Target Class')",
+                    "        plt.tight_layout()",
+                    "        plt.show()",
+                    "        plt.close('all')",
+                    "",
+                ])
+
+        return "\n".join(lines)
+
+    # -------------------------------------------------------------------------
+    # 4. Master Plot Generator
+    # -------------------------------------------------------------------------
+    def generate_all_plots_code(self) -> str:
+        """Combine all visualization modules into a cohesive EDA script block."""
+        blocks = [
+            self.generate_univariate_code(),
+            self.generate_correlation_code(),
+            self.generate_target_plots_code(),
+        ]
+        return "\n\n".join(blocks)

data_advisor-0.1.0.dist-info/METADATA

@@ -0,0 +1,303 @@
+Metadata-Version: 2.4
+Name: data_advisor
+Version: 0.1.0
+Summary: A production-grade diagnostic and code generation advisor for timed data analysis exams and rapid exploratory data science.
+Author: Principal Data Science Architect
+License-Expression: MIT
+Keywords: data-analysis,eda,data-science,hypothesis-testing,code-generation,machine-learning,automated-eda,pandas,scipy,scikit-learn
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Education
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Software Development :: Code Generators
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: pandas>=2.0.0
+Requires-Dist: numpy>=1.24.0
+Requires-Dist: scipy>=1.10.0
+Requires-Dist: scikit-learn>=1.2.0
+Requires-Dist: matplotlib>=3.7.0
+Requires-Dist: seaborn>=0.12.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
+
+# DataAdvisor (data_advisor)
+
+> **Autonomous Data Science Diagnostic Engine & Exam Code Generator**  
+> Engineered for students, practitioners, and data scientists to audit unknown datasets, formulate statistical hypotheses, and generate copy-pasteable, production-ready Python pipelines during timed data analysis examinations.
+
+---
+
+## 🚀 Key Highlights
+
+1. **Deterministic Auditing Engine**: Deeply profiles any `pd.DataFrame` (or CSV, TSV, Excel, Parquet file) in seconds.
+2. **Automated Hypothesis Testing**:
+   - Numeric vs. Numeric: **Pearson** & **Spearman** correlations with $p$-values.
+   - Categorical vs. Categorical: **Chi-Square Test of Independence** with Cramér's V effect size.
+   - Numeric vs. Binary Target: **Welch's Two-Sample t-test** & **Mann-Whitney U test**.
+   - Numeric vs. Multi-class Target: **One-Way ANOVA** ($F$-test) & **Kruskal-Wallis $H$-test**.
+3. **Outlier & Skewness Diagnostics**: Combines **IQR fences (1.5× and 3.0×)** and **Z-score criteria ($|z| > 3$)**; automatically recommends `np.log1p`, Yeo-Johnson power transformations, or winsorization.
+4. **Target & Model Strategy Selector**: Automatically identifies whether the task is **Regression** or **Classification** (Binary or Multiclass), detects critical class imbalance, and selects baseline models (`LogisticRegression`, `Ridge`, `RandomForest`).
+5. **Copy-Pasteable Code Generator**: Emits clean, PEP 8 compliant, runnable Python scripts containing complete Pandas, Scipy, and Scikit-Learn code tailored to the audited dataset.
+
+---
+
+## 📦 Installation
+
+To install `data_advisor` in editable mode directly from your local repository:
+
+```bash
+# Navigate to the project root directory
+cd "path/to/Custom Library"
+
+# Install in editable mode with dependencies
+pip install -e .
+```
+
+### Verified Dependencies
+- Python `>= 3.9`
+- `pandas >= 2.0.0`
+- `numpy >= 1.24.0`
+- `scipy >= 1.10.0`
+- `scikit-learn >= 1.2.0`
+- `matplotlib >= 3.7.0`
+- `seaborn >= 0.12.0`
+
+---
+
+## ⚡ Quickstart: The 1-Line Exam Workflow
+
+When handed an unfamiliar exam dataset (`exam_dataset.csv`), run the top-level `data_advisor` function in your Jupyter Notebook or Python terminal:
+
+```python
+from data_advisor import data_advisor
+
+# 1-Line Diagnostic & Code Generation:
+# Outputs:
+# 1. Full diagnostic report stating what all analysis to perform
+# 2. Executable, copy-pasteable Python code to execute all steps
+data_advisor("exam_dataset.csv")
+```
+
+Or with an optional target column or output script:
+```python
+data_advisor("exam_dataset.csv", target="churn", output_script="solution.py")
+```
+
+You can also use the object-oriented API:
+```python
+from data_advisor import DataAdvisor
+
+advisor = DataAdvisor("exam_dataset.csv", target="churn", id_cols=["customer_id"])
+advisor.report()                          # Diagnostic report
+advisor.generate_script("solution.py")    # Full Python script
+clean_code = advisor.get_code_block("cleaning")  # Specific stage code
+```
+
+Or directly from your command-line terminal:
+```bash
+# Diagnostic report + code prompt
+data-advisor exam_dataset.csv
+
+# Print complete executable Python code directly to the terminal
+data-advisor exam_dataset.csv --code
+
+# Save complete pipeline to a Python file
+data-advisor exam_dataset.csv --output solution.py
+```
+
+---
+
+## 🔍 Instant Code Snippet Search: `search(key)`
+
+`data_advisor` includes a search engine that searches **any keyword** across your own local code folder (`code_bank/`).
+
+### How It Works:
+1. **Your Folder**: Simply paste your custom Python scripts (`.py`), Jupyter Notebooks (`.ipynb`), Arduino/ESP32 sketches (`.ino`, `.cpp`), or text files into `code_bank/`.
+2. **Dynamic Scanning**: The search engine scans `code_bank/` in real time on every search call—no indexing or restarts required. You can add, edit, or delete files anytime.
+3. **Any Keyword**: Search for single terms, phrases, or keyword lists.
+
+```python
+from data_advisor import search
+
+# 1. List all available snippets in your code_bank
+search()
+
+# 2. Search for any keyword (e.g., machine learning, IoT, algorithms)
+search("linear regression")
+search("dht22")
+search("kmeans")
+search("wokwi")
+
+# 3. Search with multiple keywords or a list
+search(["esp32", "temperature"])
+search("decision tree, entropy")
+
+# 4. Search within a custom directory
+search("apriori", folder="my_other_codes")
+```
+
+Or search directly via the CLI:
+```bash
+# List all files currently in code_bank
+data-advisor --search "list"
+
+# Search for any keyword
+data-advisor --search "linear regression"
+data-advisor --search "wokwi"
+```
+
+---
+
+## 📄 Complete File Viewing, Retrieval & Execution: `get_file()`, `read_file()`, `run_file()`
+
+To retrieve or execute the **entire complete code file** from `code_bank/` (not just search snippets):
+
+### 1. View / Print Complete File
+```python
+from data_advisor import get_file, view_file
+
+# By question number:
+get_file("q1")                     # Complete code for Question 1
+get_file(24)                       # Complete code for Question 24
+get_file("q32", line_numbers=True) # With line numbers
+
+# By filename or keyword:
+get_file("sketch.ino")             # Arduino / ESP32 sketch
+get_file("subscriber.py")
+```
+
+### 2. Retrieve Complete Raw Code String (No Printing)
+```python
+from data_advisor import read_file
+
+# Return complete raw code as a Python string
+code_string = read_file("q24")
+print(f"Loaded {len(code_string)} characters")
+```
+
+### 3. Run Any File Directly
+```python
+from data_advisor import run_file
+
+# Execute a Python file directly via subprocess
+run_file("q24")
+run_file("iss")
+```
+
+### 4. Direct CLI Commands
+```bash
+# Print complete file to console
+data-advisor --get q1
+data-advisor -g q24 --line-numbers
+data-advisor --get sketch.ino
+
+# Execute script directly
+data-advisor --run q24
+data-advisor -r 14
+
+# List all available code files
+data-advisor --list
+```
+
+
+
+---
+
+## 🧠 Decision Rules Matrix
+
+### 1. Data Cleaning & Integrity Rules
+| Condition | Severity | Recommended Action | Generated Code |
+| :--- | :--- | :--- | :--- |
+| **Duplicates Detected** (`> 0`) | `WARNING` / `CRITICAL` | Drop duplicate rows | `df = df.drop_duplicates().reset_index(drop=True)` |
+| **High Missingness** (`>= 60%`) | `CRITICAL` | Drop column entirely | `df = df.drop(columns=[col])` |
+| **Low Missingness** (`< 5%`) | `INFO` | Impute median (num) / mode (cat) | `df[col] = df[col].fillna(df[col].median())` |
+| **Moderate Missingness** (`5% - 60%`) | `WARNING` | Skewed: Median; Symmetric: Mean | `SimpleImputer(strategy='median')` |
+| **Constant Column** (variance = 0) | `CRITICAL` | Drop column | `df = df.drop(columns=[col])` |
+| **Identifier Column** (IDs, hashes) | `WARNING` | Exclude from feature matrix $X$ | `X = df.drop(columns=[id_col])` |
+| **Date String Column** | `RECOMMENDED` | Parse date & extract temporal features | `.dt.year`, `.dt.month`, `.dt.dayofweek` |
+
+### 2. Distribution & Outlier Rules
+| Metric | Condition | Transformation Strategy | Rationale |
+| :--- | :--- | :--- | :--- |
+| **Skewness** | $> 1.2$ (Non-negative) | `np.log1p(df[col])` | Stabilizes variance, compresses long positive tail |
+| **Skewness** | $> 1.2$ (Contains negatives) | `PowerTransformer(method='yeo-johnson')` | Normalizes non-Gaussian data with non-positive values |
+| **Skewness** | $< -1.2$ (Left-skewed) | `PowerTransformer(method='yeo-johnson')` | Corrects severe left tail |
+| **IQR Outliers** | $> 5\%$ of samples | IQR clipping / `RobustScaler()` | Caps extreme leverage points |
+
+### 3. Categorical Processing Rules
+| Cardinality | Encoding Strategy | Implementation |
+| :--- | :--- | :--- |
+| **Binary** ($2$ levels) | Direct Binary Mapping ($0/1$) | `df[col].map({'No': 0, 'Yes': 1})` |
+| **Low-to-Medium** ($3$ to $10$ levels) | One-Hot Encoding (`drop_first=True`) | `pd.get_dummies(..., drop_first=True, dtype=int)` |
+| **High** ($> 10$ levels) | Frequency Encoding / Target Encoding | `df[col].map(df[col].value_counts(normalize=True))` |
+
+### 4. Hypothesis Testing Decision Engine
+| Variable Types | Primary Test | Non-Parametric Alternative | Effect Size Metric |
+| :--- | :--- | :--- | :--- |
+| **2 Numeric Features** | Pearson Correlation ($r, p$) | Spearman Rank Correlation ($\rho, p$) | Correlation Coefficient ($r$) |
+| **2 Categorical Features** | Chi-Square Test of Independence ($\chi^2$) | Fisher's Exact Test (for $2\times 2$) | Cramér's $V$ |
+| **1 Numeric + 1 Binary Cat** | Welch's Independent $t$-test | Mann-Whitney $U$ test | Cohen's $d$ / Rank-biserial |
+| **1 Numeric + 1 Multi-class Cat** | One-Way ANOVA ($F, p$) | Kruskal-Wallis $H$-test | Eta-squared ($\eta^2$) |
+
+### 5. Target Variable & Model Baseline Matrix
+| Target Type | Detected Problem | Imbalance Threshold | Recommended Baselines | Evaluation Metrics |
+| :--- | :--- | :--- | :--- | :--- |
+| **Continuous Numeric** | Regression | N/A | Linear Regression, Ridge ($L_2$), Random Forest Regressor | RMSE, MAE, $R^2$ Score |
+| **Binary / Discrete** | Classification | Minority $< 20\%$ (Ratio $\ge 3:1$) | Logistic Regression (`class_weight='balanced'`), Random Forest Classifier | F1-Score, PR-AUC, ROC-AUC, Confusion Matrix |
+
+---
+
+## 📂 Project Architecture
+
+```
+Custom Library/
+├── pyproject.toml                     # Modern setuptools packaging & dependency metadata
+├── README.md                          # Comprehensive library documentation & exam cheat sheet
+├── src/
+│   └── data_advisor/
+│       ├── __init__.py                # Package exports (DataAdvisor, DataScanner, RuleEngine)
+│       ├── advisor.py                 # Primary facade class & CLI reporter
+│       ├── scanner.py                 # Core profiling engine & statistical test runner
+│       ├── rules.py                   # Heuristic recommendation engine & severity prioritizer
+│       ├── codegen.py                 # Sequential Python script & code block generator
+│       ├── visualizer.py              # Publication-ready Matplotlib & Seaborn code generator
+│       └── cli.py                     # Command-line entry point (`data-advisor`)
+├── tests/
+│   └── test_advisor.py                # Automated pytest suite covering regression & classification
+└── examples/
+    ├── demo_exam_workflow.py          # End-to-end exam simulation walkthrough
+    ├── student_exam_data.csv          # Sample dataset with outliers, nulls, and duplicates
+    └── generated_analysis_pipeline.py # Fully generated, executable production script
+```
+
+---
+
+## 🧪 Running Tests
+
+Run the test suite using `pytest`:
+
+```bash
+python -m pytest -v
+```
+
+All tests inspect and validate:
+- Missing value audit & column dropping (>60%).
+- Identifier and constant column detection.
+- Skewness and IQR/Z-score outlier calculations.
+- Parametric and non-parametric hypothesis testing.
+- Target classification and regression auto-detection.
+- Full end-to-end Python script code generation and execution.
+
+---
+
+## 📜 License
+MIT License. Built for rigorous data science education, competitive coding, and exam excellence.

data_advisor-0.1.0.dist-info/RECORD

@@ -0,0 +1,14 @@
+data_advisor/__init__.py,sha256=4TULFgIzA0A-QUthWOvpgsOtMII6VRybzEpe8M6umtw,879
+data_advisor/__main__.py,sha256=J4_2-KC-FORv8kBEJE0TPqbDlwY80l4Uto8BewcKdkQ,191
+data_advisor/advisor.py,sha256=nv-UR0tDFEJ60FksqISm-3NkjZFScIRXQKwx2CEc3Bo,19063
+data_advisor/cli.py,sha256=GKwtctPR-lM2zFna4gCQy3IDA9SlH503gIx5gIXyH_k,5370
+data_advisor/codegen.py,sha256=zkIgVNSXusrmZ5Y8cjSS7_c2UNOWl8MDY23tc08f1NM,24989
+data_advisor/rules.py,sha256=QuBDOvdQGhQ7gohFFsOIbyaIk95r5DaeIHIkr0J7HGk,19174
+data_advisor/scanner.py,sha256=NQzwq4pT8dlrOHPUS_O4SaFe_66eELJP7huvtot_Ay0,30645
+data_advisor/search.py,sha256=bSkCE6RUxvOxaLv6Vg2lS9xSfXjBV8xeFz4CS4VMHiU,24980
+data_advisor/visualizer.py,sha256=VhlQZEePVZm1Lpn0Q7wS1LcZZtS6saW28_xDSjVQuB0,12188
+data_advisor-0.1.0.dist-info/METADATA,sha256=8uNX0f6S1ypFgNaKhBATKtdgaqsch1q_1-D7GIoTB8g,12732
+data_advisor-0.1.0.dist-info/WHEEL,sha256=mOdXR9C3wMVov7cSY8PY-XCzo3SmmWCHvGQr5csJoao,91
+data_advisor-0.1.0.dist-info/entry_points.txt,sha256=VduGLJ3bCfhCe5hL6dKjRbr0V4VbMv059LZrdIFDaAI,55
+data_advisor-0.1.0.dist-info/top_level.txt,sha256=CPvucnS0dOg3PgL7a7fl_JmuxdZrWRXQJqEbjJ_Z0hg,13
+data_advisor-0.1.0.dist-info/RECORD,,

data_advisor-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (84.2.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

data_advisor-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+data-advisor = data_advisor.cli:main

data_advisor-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+data_advisor