Hello, it is Yope! I am a liberal arts student, but I was interested in the possibilities of AI, so I went to the AI-specialized school "Aidemy" to study. I would like to share the knowledge gained here with you, and I am summarizing it on Qiita. I am very happy that many people have read the previous summary article. Thank you! This is the first post of machine learning pre-processing. Nice to meet you.
What to learn this time ・ Data analysis flow
-As the flow (process) of data analysis, CRISP-DM and KDD have been proposed. CRISP-DM -CRISP-DM has the following process. ① __ Business understanding __: Clarify what the issues are and what to do with data analysis. ② __ Data understanding __: Understand whether data can be acquired and analyzed. ③ __ Data preparation __: Format the data into a form that can be used in ④ modeling. ④ __ Modeling __: Apply a model to the data and analyze it. ⑤ __ Evaluation __: Evaluate whether the analysis result is sufficient. ⑥ __Apply __: Actually apply the analysis results to issues and tasks.
-However, these processes are not necessarily one-way, and may return if necessary. ・ The pre-processing of the data learned this time corresponds to (2) and (3) of this process.
・ Figure![Screenshot 2020-10-29 14.36.04.png](https://qiita-image-store.s3.ap-northeast-1.amazonaws.com/0/698700/d949cd2a-4ff7-833e- d8b1-df799dcf7741.png)
KDD -KDD has the following process. ① __ Data acquisition __: Set issues and goals and acquire data. ② __Data selection __: Select the data to be used for analysis (data mining) from the acquired data. ③ __Data cleansing __: Performs data cleansing such as deleting missing values and outliers. ④ __Data conversion : Converts the cleansed data format to a format that can be used for data mining. ⑤__Data mining: Performs regression and classification on the converted data for analysis and learning. ⑥ __ Interpretation / Evaluation __: Interpret and evaluate the pattern from the results obtained by data mining.
・ Figure![Screenshot 2020-10-29 14.36.19.png](https://qiita-image-store.s3.ap-northeast-1.amazonaws.com/0/698700/78ad3832-30bf-33c2- 4788-44865de4cc74.png)
This time is over. Thank you for reading until the end.