If you are already familiar with the module/package loading methods of Python and R, the following table is relatively easy to find.
Python is referenced in the following table as a module. Some modules are not native modules. Please use pip install * to install;
For the same reason, in order to facilitate indexing, R also refers to:: indicates the function and the name of the package where the function is located. If it does not contain :: indicates that it is in the default package of R, such as::, please use install.packages("*") to finish the installation.
Connector & IO
Database
| 类别 | Python | R |
|---|---|---|
| MysqL | mysql-connector-python(官方) | RMysqL |
| Oracle | cx_Oracle | ROracle |
| Redis | redis | rredis |
| MongoDB | pymongo | RMongo, rmongodb |
| neo4j | py2neo | RNeo4j |
| Cassandra | cassandra-driver | RJDBC |
| ODBC | pyodbc | RODBC |
| JDBC | 未知[Jython Only] | RJDBC |
IO
| 类别 | Python | R |
|---|---|---|
| excel | xlsxWriter, pandas.(from/to)_excel, openpyxl | openxlsx::read.xlsx(2), xlsx::read.xlsx(2) |
| csv | csv.writer | read.csv(2), read.table |
| json | json | jsonlite |
| 图片 | PIL | jpeg, png, tiff, bmp |
Statistics
| 类别 | Python | R |
|---|---|---|
| 描述性统计汇总 | scipy.stats.descirbe | summary |
| 均值 | scipy.stats.gmean(几何平均数), scipy.stats.hmean(调和平均数), numpy.mean, numpy.nanmean, pandas.Series.mean | mean |
| 中位数 | numpy.median, numpy.nanmediam, pandas.Series.median | median |
| 众数 | scipy.stats.mode, pandas.Series.mode | 未知 |
| 分位数 | numpy.percentile, numpy.nanpercentile, pandas.Series.quantile | quantile |
| 经验累积函数(ECDF) | statsmodels.tools.ECDF | ecdf |
| 标准差 | scipy.stats.std, scipy.stats.nanstd, numpy.std, pandas.Series.std | sd |
| 方差 | numpy.var, pandas.Series.var | var |
| 变异系数 | scipy.stats.variation | 未知 |
| 协方差 | numpy.cov, pandas.Series.cov | cov |
| (Pearson)相关系数 | scipy.stats.pearsonr, numpy.corrcoef, pandas.Series.corr | cor |
| 峰度 | scipy.stats.kurtosis, pandas.Series.kurt | e1071::kurtosis |
| 偏度 | scipy.stats.skew, pandas.Series.skew | e1071::skewness |
| 直方图 | numpy.histogram, numpy.histogram2d, numpy.histogramdd | 未知 |
Regression (including statistics and machine learning)
| 类别 | Python | R |
|---|---|---|
| 普通最小二乘法回归(ols) | statsmodels.ols, sklearn.linear_model.LinearRegression | lm, |
| 广义线性回归(gls) | statsmodels.gls | nlme::gls, MASS::gls |
| 分位数回归(Quantile Regress) | statsmodels.QuantReg | quantreg::rq |
| 岭回归 | sklearn.linear_model.Ridge | MASS::lm.ridge, ridge::linearRidge |
| LASSO | sklearn.linear_model.Lasso | lars::lars |
| 最小角回归 | sklearn.linear_modle.Lassolars | lars::lars |
| 稳健回归 | statsmodels.RLM | MASS::rlm |
Hypothetical Test
| 类别 | Python | R |
|---|---|---|
| t检验 | statsmodels.stats.ttest_ind, statsmodels.stats.ttost_ind, statsmodels.stats.ttost.paired; scipy.stats.ttest_1samp, scipy.stats.ttest_ind, scipy.stats.ttest_ind_from_stats, scipy.stats.ttest_rel | t.test |
| ks检验(检验分布) | scipy.stats.kstest, scipy.stats.kstest_2samp | ks.test |
| wilcoxon(非参检验，差异检验) | scipy.stats.wilcoxon, scipy.stats.mannwhitneyu | wilcox.test |
| Shapiro-Wilk正态性检验 | scipy.stats.shapiro | shapiro.test |
| Pearson相关系数检验 | scipy.stats.pearsonr | cor.test |
Time series
| 类别 | Python | R |
|---|---|---|
| AR | statsmodels.ar_model.AR | ar |
| ARIMA | statsmodels.arima_model.arima | arima |
| VAR | statsmodels.var_model.var | 未知 |
Mechine Learning
版权声明：本文内容由互联网用户自发贡献，该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容， 请发送邮件至 [email protected] 举报，一经查实，本站将立刻删除。
