Skip to main content

New Value Analysis

new_value_analysis는 **신규가치분석(New Value Analysis)**을 수행하기 위한 Python 기반 분석 유틸리티 라이브러리입니다.

텍스트 데이터 기반으로 Action(행동) → Actor(행위자) → Opportunity Area(기회영역) 분석 파이프라인을 일관된 구조로 수행할 수 있도록 설계되었습니다.


📦 Installation

pip install new_value_analysis

Python 3.9 이상 권장


📚 Core Concept

본 라이브러리는 다음과 같은 3단계 분석 흐름을 전제로 합니다.

[Action Finder]
텍스트 데이터 → 토픽 모델링 → 행동(Action) 정의

[Actor Finder]
문서 임베딩 → 군집 분석 → 행위자(Actor) 유형화

[Opportunity Area Analysis]
중요도 × 만족도 → 기회영역(Opportunity Area) 도출

📁 Package Structure

new_value_analysis
├─ action_finder
│  ├─ topic_modeling.py          # LDA 학습
│  ├─ find_topicnum.py           # 토픽 수 탐색
│  └─ select_action_number.py    # 문서별 Action 번호 할당
│
├─ actor_finder
│  ├─ doc2vec.py                 # Doc2Vec 임베딩
│  ├─ find_right_silhouette.py   # 최적 군집 수 탐색
│  ├─ silhouette_plot.py         # 실루엣 플롯
│  └─ visualize_dendrogram.py    # 덴드로그램 시각화
│
└─ opportunity_area_analysis
   ├─ satisfaction_scaling.py    # 점수 스케일링
   └─ opportunity_plot.py        # Opportunity Area 시각화

1️⃣ Action Finder

목적

  • 텍스트 데이터에서 **행동(Action)**을 추출
  • 문서별로 어떤 행동을 가장 강하게 드러내는지 식별

주요 기능

from new_value_analysis.action_finder import (
    LDA_train,
    assign_action_number
)

예시 흐름

# 1. LDA 모델 학습
lda_model, corpus, dictionary = LDA_train(texts)

# 2. 문서별 Action 번호 할당
df["action_number"] = assign_action_number(lda_model, corpus)

2️⃣ Actor Finder

목적

  • 문서를 행위자(Actor) 관점에서 군집화
  • “어떤 유형의 사람이 어떤 행동을 하는가?”를 구조화

주요 기능

from new_value_analysis.actor_finder import (
    train_doc2vec_module,
    agglomerative_silhouette_module,
    visualize_silhouette,
    plot_dendrogram
)

예시 흐름

# 1. Doc2Vec 임베딩
model, vectors, tagged_docs = train_doc2vec_module(
    df,
    token_col="tagged_review"
)
df["vector"] = vectors

# 2. 최적 군집 수 탐색
scores, best_k = agglomerative_silhouette_module(df)

# 3. 군집 품질 시각화
visualize_silhouette([2, 3, 4, 5], vectors)

# 4. 덴드로그램 확인
plot_dendrogram(df)

3️⃣ Opportunity Area Analysis

목적

  • 중요도 × 만족도 기반으로 기회영역(Opportunity Area) 도출
  • “노력 대비 가치가 큰 영역”을 시각적으로 식별

주요 기능

from new_value_analysis.opportunity_area_analysis import (
    minmax_scale_scores,
    plot_opportunity_area
)

예시 흐름

# 1. 점수 스케일링
df_scaled = minmax_scale_scores(df)

# 2. Opportunity Area 시각화
plot_opportunity_area(
    importance=df_scaled["importance"],
    satisfaction=df_scaled["satisfaction"],
    labels=df_scaled["action_label"]
)

텍스트 수집
   ↓
전처리 / 토큰화
   ↓
Action Finder (행동 정의)
   ↓
Actor Finder (행위자 유형화)
   ↓
Opportunity Area Analysis (기회영역 도출)

🎓 Use Cases

  • AI 서비스 기획 / UX 리서치
  • VOC / 리뷰 데이터 기반 서비스 개선
  • 공공 데이터 기반 정책 기획
  • 교육 과정(부트캠프) 분석 프로젝트

✨ Versioning

  • v0.1.0

    • Initial public release
    • Action / Actor / Opportunity 분석 파이프라인 제공

Metadata

Release files for new-value-analysis 0.1.3

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for new-value-analysis 0.1.3
File Size Uploaded Provenance
new_value_analysis-0.1.3.tar.gz 14.5 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for new-value-analysis 0.1.3
File Interpreter ABI Platform
new_value_analysis-0.1.3-py3-none-any.whl Python 3 none any Details

Total release size: 32.3 kB

Release files / new_value_analysis-0.1.3.tar.gz

Download URL new_value_analysis-0.1.3.tar.gz
Size 14.5 kB
Tags Source
SHA-256 checksum
How to use checksums
4290bb780a2d739c4d4128b323e05c23216b553856687b1aabeb6993c82704dc
BLAKE2b-256 checksum
How to use checksums
896479da4aa44dddcb6c418347ef602f18598652efef58c5daf73a5e6e278971
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.13.4

Release files / new_value_analysis-0.1.3-py3-none-any.whl

Download URL new_value_analysis-0.1.3-py3-none-any.whl
Size 17.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
35056d8d33b65db6fc52cb3fcee0d69bd85970ac15324b231ee8c7ce08132b7f
BLAKE2b-256 checksum
How to use checksums
8d978c61edaa2b51f7cdb60310d5be3a67d8f83d1d232da0537166a45eb98345
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.13.4

Security for new-value-analysis 0.1.3

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page