인간의 창의력과 노동력을 보완하기 위해 다양한 도구들이 발명되었습니다. 예를 들어, 구석기 시대에는 철기 도구의 발명으로 인해 인간은 작업을 더 효율적으로 수행할 수 있게 되었고, 이후 기계의 발명으로 생산성이 크게 증가하였습니다. 그러나 이러한 발전은 동시에 빈부 격차를 야기하기도 했습니다. 기계 조작을 배운 사람과 배우지 못한 사람 간의 소득 격차가 발생하였습니다.

컴퓨터와 인터넷의 발전은 국가 간의 빈부 격차를 더욱 심화시켰습니다. 정보와 지식에 대한 접근성이 개인 및 국가 간의 차이를 넓혔습니다. 선진국과 후진국으로 나누어진 사회에서 정보를 이해하고 활용하는 능력은 경제적 발전과 교육 수준과 직결되었습니다.

이제 인공지능의 발전으로 현재와 과거의 데이터를 학습하여 미래를 예측하는 것이 가능해졌습니다. 이는 전문가의 도움 없이 누구나 전문적인 지식을 얻을 수 있는 사회로의 진입을 열어주었습니다. 머신러닝은 이러한 인공지능의 핵심 기술 중 하나로, 데이터를 지도학습, 비지도학습, 강화학습 등의 알고리즘을 통해 컴퓨터에게 학습시키는 과정입니다.

이 책은 넘파이, 판다스, 시각화 라이브러리, 텐서플로우, 사이킷런 등 다양한 머신러닝 관련 라이브러리를 활용하여 구글 코랩 환경에서 프로그램을 작성하고 실행하는 방법을 소개합니다. 예제들은 주로 간단한 데이터를 활용하여 코딩하고 실행함으로써 일반인들도 머신러닝의 개념과 활용 방법을 쉽게 이해할 수 있습니다. 이를 통해 데이터 분석과 예측에 대한 이해를 갖게 됩니다. 이를 토대로 최적화된 생산 시스템과 더 나은 미래를 향한 발전을 이루는 데 도움이 될 것입니다.

1장. 머신러닝 지식
머신러닝의 개요 ············································································································· 1
머신러닝의 종류 ············································································································· 6
머신러닝의 사이킷 런 ································································································· 10
데이터 ···························································································································· 11
머신러닝 프로세스 ······································································································· 19

2장. 머신러닝 라이브러리
머신러닝의 Python ······································································································ 22
Tensor Flow ·················································································································· 31
Scikit-learn ···················································································································· 42
Numpy ·························································································································· 55
Pandas ··························································································································· 66
Matplotlib ····················································································································· 79

3장. 머신러닝 기초
지도학습 및 비지도학습 ····························································································· 87
데이터 시각화 및 요약 ······························································································· 93

4장. 머신러닝 Linear Regression
선형회귀 모델 과정 ··································································································· 102
선형모델 성능 개선 ··································································································· 108
선형회귀 예제-1 ········································································································· 111
선형회귀 예제-2 ········································································································· 117
Scikit-learn 선형회귀 ································································································· 120
Multivariate Regression ···························································································· 131
Nonlinear Regression ································································································ 143

5장. 지도학습-Classification
Logistic Regression ··································································································· 147
Decision Tree ············································································································· 161
SVM ····························································································································· 176
kNN ····························································································································· 185
Time Series(시계열) ··································································································· 190

6장. 비지도학습
Clustering ···················································································································· 205
K-means ······················································································································ 206
Reinforcement ············································································································ 216