DS 学习打卡贴

FEB 20： Machine learning with linear regression and logistic regression. (1) Check data with .head(), info(), etc (2) Exploratory data analysis (3) clean data, impute or drop missing values, change category variable to 0/1, e.g. sex. (4) divide into train and test (train_test_split) and fit, predict. (5) linear regression, check residual, and line plot of y_test vs prediction. (6) Logistic regression: confusion matrix or classification matrix

K nearest neighbours

FEB 20： Machine learning with linear regression and logistic regression. (1) Check data with .head(), info(), etc (2) Exploratory data analysis (3) clean data, impute or drop missing values, change category variable to 0/1, e.g. sex. (4) divide into train and test (train_test_split) and fit, predict. (5) linear regression, check residual, and line plot of y_test vs prediction. (6) Logistic regression: confusion matrix or classification matrix

K nearest neighbours

FEB 20： Machine learning with linear regression and logistic regression. (1) Check data with .head(), info(), etc (2) Exploratory data analysis (3) clean data, impute or drop missing values, change category variable to 0/1, e.g. sex. (4) divide into train and test (train_test_split) and fit, predict. (5) linear regression, check residual, and line plot of y_test vs prediction. (6) Logistic regression: confusion matrix or classification matrix

FEB 20： Machine learning with linear regression and logistic regression. (1) Check data with .head(), info(), etc (2) Exploratory data analysis (3) clean data, impute or drop missing values, change category variable to 0/1, e.g. sex. (4) divide into train and test (train_test_split) and fit, predict. (5) linear regression, check residual, and line plot of y_test vs prediction. (6) Logistic regression: confusion matrix or classification matrix

aKisspy 发表于 2017-1-23 13:41
new grad找工作！同打卡。已经刷完了绿皮的brain teaser和coursera 的machine learning。现在在搞R打projec ...

你说的绿皮的 brain teaser 能给个链接吗 或者大概什么样的 找不到呢，，，

FEB 23: Learn the below machine algorithms
1. Linear regression
2. Logistic Regression
3. Decision Tree
4. SVM
5. Naive Bayes
6. KNN
7. K-Means
8. Randon Forest
9. Dimension Reduction algorithm

good job

自我心理暗示一下，干好现在的本职工作。Try not to find trouble for myself. 其它一切时间和精力都奉献给找到最好的DS工作。 加油！

Feb 26: 完成KAGGLE Titanic data competition

Feb 28: Nonparametric inference. When population distribution is not know. 1. Inference on one sample mean: 1.1 Sign test, 1.2 Wilcoxon signed rank test. 2. Inference on two sample mean: Wilcoxon Mann-White test. 3. Inference on more than two population means: Krustal-Wallis test.

Parametric inference, assume population is normal. 1. inference on one sample mean. 1.1 population STD sigma know: Z-test, 1.2 sigma not know and estimated by sample STD s: t-test. 1.3 Large sample, approximate Z-test. 2. Inference on two sample mean: t-test 3. Inference on the means of more than two samples: ANOVA

The nonparametric version of the Pearson correlation coefficient is the Spearman rank correlation and Kendall rank correlation.