get-env-info.qmd

---
title: "Tidy env info"
format: pdf
editor: visual
---

# Load the csv file and tidy the data

```{r}
library(tidyverse)


# Load the csv file
env_info <- read_csv("C:\\Users\\DuYih\\Desktop\\sequence-PVC.csv")


```

```{r}
env_info
```


```{r}
# Tidy the data
env_info %>% group_by(Project, `Isolation Source`) %>% 
  summarise(count=n())
```

```{r}
env_info %>% group_by(Project) %>% 
  summarise(count=n())
```


```{r}
env_info %>% filter(Project == "PRJNA39207") %>% 
  group_by(Project, `Isolation Source`) %>% 
  summarise(count=n())

```



```{r}
# select the FJ901344 information
env_info %>% filter(Accession == "FJ902144") 
head(env_info)
```

```{r}
env_info %>% filter(Project == 'PRJNA38465')
```

```{r}
# 读取CSV文件
file_path <- "C:\\Users\\DuYih\\Desktop\\github\\PVC\\env_abundance.csv"
data <- read.csv(file_path, stringsAsFactors = FALSE)

# 检查是否存在字符 'FJ902375'
exists <- any(grepl("ERP013152", data))

# 输出结果
if (exists) {
  print("字符 'FJ902375' 存在于文件中。")
} else {
  print("字符 'FJ902375' 不存在于文件中。")
}

```



```{r}
# 读取文件的前几行
file_path <- "C:\\Users\\DuYih\\Desktop\\github\\PVC\\samples.info"

# 使用 read.csv 函数的 nrows 参数读取前几行
num_rows <- 50  # 你想查看的行数

data <- read.csv(file_path, nrows = num_rows)

# 显示数据
print(data)

```

grep -q 'FJ902375' samples-otus.99.metag.minfilter && echo "字符 'FJ902375' 存在于文件中。" || echo "字符 'FJ902375' 不存在于文件中。"