Menu
Sub-skill of pandas-data-processing: 2. Statistical Analysis.
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/vamseeachanta/workspace-hub --skill pandas-data-processing-2-statistical-analysisThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Write outbound email and external messages in Vamsee Achanta's voice — a subtle offer to help, never bold or rash claims. Load before drafting ANY email, LinkedIn/Collide reply, proposal note, or outreach sent under his name.
Save/publish analysis or computation results from ANY ecosystem repo to Hugging Face as a queryable, viewer-renderable dataset. Use when the user wants to "save results to hugging face", "publish dataset to HF", "hugging face data saving", "save analysis results", "hf dataset", "make results queryable", or "render via datasets-server API". Reshapes nested results into flat parquet tables, writes a dataset card with a viewer `configs:` block and provenance, applies license/public-vs-private routing, enforces a domain data-quality gate (faithful-to-source != correct), publishes to `aceengineer/<repo>-<projection>`, and verifies via the datasets-server API.
Clone, create, fork, configure, and manage GitHub repositories. Manage remotes, secrets, releases, and workflows. Works with gh CLI or falls back to git + GitHub REST API via curl.
Showing SKILL.md
Based on SOC occupation classification
| name | pandas-data-processing-2-statistical-analysis |
| description | Sub-skill of pandas-data-processing: 2. Statistical Analysis. |
| version | 1.0.0 |
| category | data |
| type | reference |
| scripts_exempt | true |
Summary Statistics:
def generate_statistical_summary(
df: pd.DataFrame,
columns: list = None
) -> pd.DataFrame:
"""
Generate comprehensive statistical summary.
Args:
df: Input DataFrame
columns: Columns to analyze (None = all numeric)
Returns:
DataFrame with statistical metrics
"""
if columns is None:
columns = df.select_dtypes(include=[np.number]).columns.tolist()
# Standard statistics
summary = df[columns].describe()
# Additional statistics
additional_stats = pd.DataFrame({
'median': df[columns].median(),
'skewness': df[columns].skew(),
'kurtosis': df[columns].kurtosis(),
'variance': df[columns].var()
}).T
# Combine
full_summary = pd.concat([summary, additional_stats])
return full_summary
# Example
motion_stats = generate_statistical_summary(
results,
columns=['Surge', 'Sway', 'Heave', 'Roll', 'Pitch', 'Yaw']
)
print(motion_stats)
# Export to CSV
motion_stats.to_csv('reports/motion_statistics.csv')
Extreme Value Analysis:
def extract_extreme_values(
df: pd.DataFrame,
column: str,
n_extremes: int = 10,
extreme_type: str = 'max'
) -> pd.DataFrame:
"""
Extract extreme values (max or min) from time series.
Args:
df: Input DataFrame with datetime index
column: Column to analyze
n_extremes: Number of extreme values to extract
extreme_type: 'max' or 'min'
Returns:
DataFrame with extreme events
"""
if extreme_type == 'max':
extremes = df.nlargest(n_extremes, column)
elif extreme_type == 'min':
extremes = df.nsmallest(n_extremes, column)
else:
raise ValueError("extreme_type must be 'max' or 'min'")
# Sort by time
extremes = extremes.sort_index()
return extremes
# Example: Top 10 maximum tensions
max_tensions = extract_extreme_values(
results,
column='Tension_Line1',
n_extremes=10,
extreme_type='max'
)
print("Top 10 Maximum Tensions:")
print(max_tensions[['Tension_Line1']])