Normalize and fix messy data fields using AI. Use when normalizing addresses, standardizing company names, fixing inconsistent date formats, cleaning CSV data before import, correcting typos in bulk data, normalizing phone number formats, standardizing job titles, cleaning up free-text fields, data quality improvement with AI, fixing formatting inconsistencies, bulk data normalization, preparing messy data for analysis, AI-powered data wrangling.
Standardmäßig ist der Prompt ausgewählt, der zuerst die Quelle prüft. Sie können zu einem direkten Befehl wechseln oder eine lokale Kopie herunterladen.
Quelldateien prüfen
Lesen Sie SKILL.md und alle von SkillsMP angezeigten Begleitdateien, bevor Sie sich für eine Installation entscheiden.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Ein direkter Befehl überspringt den Prüf-Prompt. Prüfen Sie die Quelle, bevor Sie ihn ausführen.
Normalize and fix messy data fields using AI. Use when normalizing addresses, standardizing company names, fixing inconsistent date formats, cleaning CSV data before import, correcting typos in bulk data, normalizing phone number formats, standardizing job titles, cleaning up free-text fields, data quality improvement with AI, fixing formatting inconsistencies, bulk data normalization, preparing messy data for analysis, AI-powered data wrangling.
ai-cleaning-data
Use DSPy to normalize and fix messy data fields at scale. The core pattern - messy field value + field type/context → cleaned value + confidence - lets you handle inconsistent addresses, company names, dates, phone numbers, and free-text fields without writing a rule for every edge case.
The most effective approach: sample anomalies first, infer normalization rules, then apply deterministically where possible and use the LM only for ambiguous cases.
Step 1 - Understand the Cleaning Task
Before writing code, clarify:
What fields need cleaning? (addresses, phone numbers, dates, company names, free-text?)
What inconsistencies exist? (typos, format variations, abbreviations, mixed languages?)
What is the target format? Always define this explicitly — otherwise the LM improvises
How many rows? This determines whether to use LM for each row or rule inference + deterministic apply
Is there a gold standard? Even 50 manually-cleaned examples make optimization possible
Step 2 - Build a Single-Field Cleaner
Start with one field type. The signature takes the messy value plus explicit format instructions.
"""Clean a messy data field to match the target format exactly.
Do not change values that are already correct.
Do not add, remove, or infer information not present in the input.
"""
str
"The raw field value to clean"
str
"Type of field, e.g. 'US phone number', 'company name', 'ISO 8601 date'"
str
"Exact target format with example, e.g. '+1 (555) 123-4567'"
str
"The cleaned value in the target format, or the original if already correct"
float
"Confidence score 0.0-1.0 that the cleaned value is correct"
bool
"True if the value was changed, False if it was already correct"
"(555)123-4567"
"US phone number"
"+1 (555) 123-4567"
print
# "+1 (555) 123-4567"
print
# 0.97
Step 3 - Common Cleaning Patterns
Address Normalization
classNormalizeAddress(dspy.Signature):
"""Normalize a US mailing address to USPS standard format.
Expand abbreviations (St → Street, Ave → Avenue, Apt → Apartment).
Capitalize properly. Do not infer or add missing components.
Preserve all components including suite/unit numbers.
"""
raw_address: str = dspy.InputField(desc="Raw address string")
city_hint: str = dspy.InputField(desc="City context if known, or empty string")
state_hint: str = dspy.InputField(desc="State context if known, or empty string")
normalized: str = dspy.OutputField(desc="USPS-format address: '123 Main Street, Suite 100, Springfield, IL 62701'")
confidence: float = dspy.OutputField(desc="Confidence 0.0-1.0")
address_cleaner = dspy.Predict(NormalizeAddress)
Company Name Standardization
classStandardizeCompany(dspy.Signature):
"""Resolve a company name variant to its canonical legal name.
Examples - 'IBM Corp.' → 'IBM', 'I.B.M.' → 'IBM', 'Mickey D' → 'McDonald's'.
Use the canonical_name field for the authoritative form.
If the variant is unrecognizable, return it unchanged.
"""
variant: str = dspy.InputField(desc="Company name variant to standardize")
canonical_name: str = dspy.OutputField(desc="Canonical company name")
confidence: float = dspy.OutputField(desc="Confidence 0.0-1.0")
is_recognized: bool = dspy.OutputField(desc="True if the company was confidently identified")
company_cleaner = dspy.Predict(StandardizeCompany)
Date Format Conversion
classNormalizeDate(dspy.Signature):
"""Convert a date string to ISO 8601 format (YYYY-MM-DD).
Handle formats like '05/04/26', 'May 4th 2026', '4-May-26', '20260504'.
If the date is ambiguous (e.g. 01/02/03), flag it.
"""
raw_date: str = dspy.InputField(desc="Raw date string in any format")
iso_date: str = dspy.OutputField(desc="Date in YYYY-MM-DD format, or empty string if unparseable")
is_ambiguous: bool = dspy.OutputField(desc="True if the date could be interpreted multiple ways")
confidence: float = dspy.OutputField(desc="Confidence 0.0-1.0")
date_cleaner = dspy.Predict(NormalizeDate)
Step 4 - Rule Inference Pipeline
For large datasets, use the LM to infer rules from a sample, then apply deterministically.
classInferNormalizationRules(dspy.Signature):
"""Analyze a sample of messy field values and infer the normalization rules needed.
Output rules as a Python-executable list of (pattern, replacement) pairs where possible.
Identify which cases require LM judgment vs. deterministic transformation.
"""
field_type: str = dspy.InputField(desc="Type of field being analyzed")
target_format: str = dspy.InputField(desc="Target format with example")
sample_values: list[str] = dspy.InputField(desc="20-50 sample messy values")
deterministic_rules: list[str] = dspy.OutputField(desc="Rules expressible as regex/replace, one per line")
ambiguous_patterns: list[str] = dspy.OutputField(desc="Patterns that need LM judgment, one per line")
rule_coverage_estimate: float = dspy.OutputField(desc="Estimated % of rows covered by deterministic rules")
import pandas as pd
import re
defbuild_cleaning_pipeline(df: pd.DataFrame, column: str, field_type: str, target_format: str):
# Sample anomalies (skip already-clean values)
sample = df[column].dropna().sample(min(50, len(df))).tolist()
rule_inferrer = dspy.Predict(InferNormalizationRules)
rules = rule_inferrer(
field_type=field_type,
target_format=target_format,
sample_values=sample
)
print(f"Deterministic rules cover ~{rules.rule_coverage_estimate:.0%} of rows")
print("Rules:", rules.deterministic_rules)
print("Needs LM:", rules.ambiguous_patterns)
return rules
Step 5 - Validated Outputs with Pydantic
Use typed outputs to catch format violations before they reach your database.
from pydantic import BaseModel, field_validator
import re
classCleanedPhone(BaseModel):
original: str
cleaned: str
confidence: float @field_validator("cleaned") @classmethoddefmust_match_e164(cls, v):
if v andnot re.match(r"^\+1 \(\d{3}\) \d{3}-\d{4}$", v):
raise ValueError(f"Phone '{v}' does not match target format +1 (NNN) NNN-NNNN")
return v
classCleanPhoneTyped(dspy.Signature):
"""Clean a US phone number to +1 (NNN) NNN-NNNN format."""
raw: str = dspy.InputField()
result: CleanedPhone = dspy.OutputField()
phone_cleaner = dspy.Predict(CleanPhoneTyped)
Step 6 - Batch Processing with Confidence Routing
Route high-confidence results to auto-accept and low-confidence ones to a human review queue.
defclean_batch(
values: list[str],
field_type: str,
target_format: str,
auto_accept_threshold: float = 0.90,
flag_threshold: float = 0.70,
) -> dict:
cleaner = dspy.Predict(CleanField)
accepted, flagged, rejected = [], [], []
for val in values:
result = cleaner(
messy_value=val,
field_type=field_type,
target_format=target_format
)
entry = {"original": val, "cleaned": result.cleaned_value, "confidence": result.confidence}
if result.confidence >= auto_accept_threshold:
accepted.append(entry)
elif result.confidence >= flag_threshold:
flagged.append(entry) # send to human reviewelse:
rejected.append(entry) # too uncertain, keep original or escalatereturn {"accepted": accepted, "flagged": flagged, "rejected": rejected}
Step 7 - Evaluate and Optimize
If you have a gold standard (even 50 rows), use it to optimize prompts.
Calling the LM on every row instead of inferring rules first. For 10K+ rows, sample 20-50 anomalous values, ask the LM to infer normalization patterns, then apply them with pandas/regex. Reserve LM calls for the ambiguous remainder.
Not specifying the target format explicitly. If you write "clean the phone number" without showing the exact target format (e.g., +1 (555) 123-4567), Claude will pick a format. Always include a concrete example in target_format.
Using dspy.Assert/dspy.Suggest for format validation. These are deprecated. Use dspy.Refine with a reward function that checks the cleaned value against your format regex:
Cleaning related fields independently. Address components (street, city, state, zip) must be normalized together — passing only the street loses context needed to expand abbreviations correctly. Pass all related fields in a single signature.
Destructive normalization. Claude may silently drop components it considers "noise" (e.g., "Suite 100", "c/o Jane Smith", legal suffixes like "LLC"). Add a meaning_preserved output field and reject or flag any cleaned value where it is False.
Cross-References
Install any skill: npx skills add lebsral/DSPy-Programming-not-prompting-LMs-skills --skill <name>
/ai-parsing-data - extract structured fields from unstructured text (complement to cleaning)
/ai-checking-outputs - validate cleaned values against schemas or business rules
/dspy-refine - iterative refinement with a reward function, for format-check loops
/dspy-modules - understand Predict, ChainOfThought, and other DSPy primitives
/ai-generating-data - generate synthetic dirty data to build eval sets
Install /ai-do if you do not have it — it routes any AI problem to the right skill and is the fastest way to work: npx skills add lebsral/DSPy-Programming-not-prompting-LMs-skills --skill ai-do
Additional resources
For worked examples (address normalizer, company name standardizer, CSV batch cleaner), see examples.md
For API signatures and parameter tables (dspy.Predict, dspy.Refine, dspy.BootstrapFewShot, module.batch), see reference.md
