Jupyter notebook → LLM-ready Markdown

Cell addresses, dependency hints and figure placeholders from a pandas + matplotlib notebook.

Converted Markdown

# Sales Analysis

## Notebook overview

- Source: `sales-analysis.ipynb` · Python 3 (python)
- Cells: 8 (5 code · 3 markdown)
- Execution: execution counts are in notebook order
- Imports: `pd`, `plt` — imported names, excluded from dependency hints

> Dependency annotations ("depends on") are approximate cell dependency hints from static regex analysis of assignments and imports — not full dataflow analysis. Re-assignments inside branches, dynamic scope tricks and string-built code can fool them.

## Cell [p1] · type:markdown · id:md01aaaa

# Sales Analysis

Monthly revenue overview for the demo dataset.

## Cell [1] · type:code · id:aa11bb22

```python
import pandas as pd
```

## Cell [2] · type:code · id:bb22cc33

```python
df = pd.read_csv("sales.csv")
df.shape
```

**Output:**

```
(120, 4)
```

## Cell [p4] · type:markdown · id:md02bbbb

## Peek at the data

## Cell [3] · type:code · id:cc33dd44

> ⚠️ depends on: `df` (defined in Cell [2])

```python
df.head()
```

**Output:**

```
  month  region  units  revenue
0   Jan   North     12   1200.0
1   Jan   South      7    700.0
2   Feb   North     15   1500.0
```

## Cell [4] · type:code · id:dd44ee55

> ⚠️ depends on: `df` (defined in Cell [2])

```python
monthly = df.groupby("month")["revenue"].sum()
monthly.head(3)
```

**Output:**

```
month
Feb    1500.0
Jan    1900.0
Name: revenue, dtype: float64
```

## Cell [5] · type:code · id:ee55ff66

> ⚠️ depends on: `monthly` (defined in Cell [4])

```python
import matplotlib.pyplot as plt

fig, ax = plt.subplots()
ax.plot(monthly.index, monthly.values)
ax.set_title("Monthly revenue")
fig
```

**Output:**

[Figure: cell_5_output_1.png]

## Cell [p8] · type:markdown · id:md03cccc

Revenue trends upward across the quarter.

Keywords: ipynb to markdown llm, jupyter notebook llm context · All examples