---
title: "Patrycja_data_wrangling"
author: "Semra Smajic"
date: "11/4/2021"
output: html_document
---
## Load the packages
```{r}
library(plyr)
#library(readr)
library(tidyverse)
#library(stringr)
library(dplyr)
#library(ggplot2)
#library(ggpubr)
#library(Hmisc)
#library(reshape2)
```

## Load the data file. Please make sure of the correct separator in your file (sep = ",")
```{r}
dataset <- read.csv("U:/Projects/3. Comparison of astrocytic protocols/10. Data included in the paper/Fig. 2/raw data/Oksanen_ObjectsPerFielddata_2_version4_mod.csv", header = TRUE, sep = ","); 

dataset <- dataset %>% rename(CellLine = 1)

```


## Basic operations on columns - data calculation
# This is creating a new column (MyNewResult) with new data that you will calculate
```{r}
dataset$TotalCellArea <- dataset$GFAPSomaMaskArea+dataset$AreaProtrusionsAll;

dataset$SomaPerTotArea <- dataset$GFAPSomaMaskArea/dataset$TotalCellArea;

dataset$ProtrusionsAreaPerTotalArea <- dataset$AreaProtrusionsAll/dataset$TotalCellArea;

dataset$ProtrusionsPerimeterPerTotalArea <- dataset$PerimeterProtrusions/dataset$TotalCellArea;




write.csv(dataset, "U:/Projects/3. Comparison of astrocytic protocols/10. Data included in the paper/Fig. 2/raw data/Oksanen_ObjectsPerFielddata_2_version4_mod_new_features_2.csv")  # Always rename your .csv file

```


## Data grouping and analysis
# https://bookdown.org/manishpatwal/bookdown-demo/basic-operations-in-r.html
# var - variance
# sd- standard deviation
# mean - mean
# sum - summary
```{r}
analyzed_dataset <- dataset %>% 
  #group_by(Well, Field) %>%    # two levels of grouping
  group_by(CellLine, Replicate) %>%        # one level of grouping
  summarise(AreaProtrusionsAllByCountNucGFAP_mean = (mean(AreaProtrusionsAllByNucGFAP, na.rm = TRUE)),
            PerimeterProtrusionsByCountNucGFAP_mean = (mean(PerimeterProtrusionsByNucGFAP, na.rm = TRUE)),
            ProtrusionsPerimeterByAreaByCountNucGFAP_mean = (mean(ProtrusionsPerimeterByAreaByNucGFAP, na.rm = TRUE)),
            GFAPSomaMaskAreaByCountNucGFAP_mean = (mean(GFAPSomaMaskAreaByNucGFAP, na.rm = TRUE)),
            ProtrusionAreaBySomaByCountNucGFAP_mean = (mean(ProtrusionAreaBySomaAreaByNucGFAP, na.rm = TRUE)),
            SkelAreaByCountNucGFAP_mean = (mean(SkelAreaByNucGFAP, na.rm = TRUE)),
            SkelAreaByProtrusionAreaByCountNucGFAP_mean = (mean(SkelAreaByProtrusionAreaByNucGFAP, na.rm = TRUE)),
            SkelAreaByProtrusionArea_mean = (mean(SkelAreaByProtrusionArea, na.rm = TRUE)),
            SkelArea_mean = (mean(SkelArea, na.rm = TRUE)),
            ProtrusionAreaBySomaArea_mean = (mean(ProtrusionAreaBySomaArea, na.rm = TRUE)),
            GFAPSomaMaskArea_mean = (mean(GFAPSomaMaskArea, na.rm = TRUE)),
            ProtrusionsPerimeterByArea_mean = (mean(ProtrusionsPerimeterByArea, na.rm = TRUE)),
            PerimeterProtrusions_mean = (mean(PerimeterProtrusions, na.rm = TRUE)),
            AreaProtrusionsAll_mean = (mean(AreaProtrusionsAll, na.rm = TRUE)),
            SomaPerTotArea_mean = (mean(SomaPerTotArea, na.rm = TRUE)),
            ProtrusionsAreaPerTotalArea_mean = (mean(ProtrusionsAreaPerTotalArea, na.rm = TRUE)),
            ProtrusionsPerimeterPerTotalArea_mean = (mean(ProtrusionsPerimeterPerTotalArea, na.rm = TRUE))
            )
write.csv(analyzed_dataset, "U:/Projects/3. Comparison of astrocytic protocols/10. Data included in the paper/Fig. 2/analyzed data/Summary_Oksanen_ObjectsPerFielddata_2_version4_mod_new_features_2.csv")    # Always rename your .csv file

```