01_descriptives_parts_a_b.Rmd

---
title: "Survey Results Task 3.3 731951"
author: "Anja Rainer"
date: "`r format(Sys.time(), '%d %B, %Y')`"
output: 
  html_document:
    keep_md: true
editor_options: 
  chunk_output_type: inline
---

```{r setup, include=FALSE}
library(tidyverse)
library(patchwork)
knitr::opts_chunk$set(echo = TRUE, warning = FALSE, dpi = 300)

df <- tar_read(with_countries)

question_codes <- tar_read(var_overview)
```



```{r remove non consenters}

# number of cases:
nrow(df)
```
Our sample is based on `r nrow(df)` cases.

# Missing data

```{r, results="asis"}
library(visdat)
vis_dat(df)
visdat::vis_miss(df)

```

```{r, fig.width=12}
df %>% 
  select_if(function(x) (sum(is.na(x)))/length(x) > .1) %>% 
  vis_miss()
```

# Demographics

# Countries

In which country do you work? [drop-down/ open text]

```{r e1, fig.width=8, fig.height=4}

e1_rec_df <- df %>%
  select("E1_rec")

e1_rec_df %>%
  mutate(E1_rec = forcats::fct_lump_min(E1_rec, min = 4, other_level = "Other")) %>%
  plot_bar(E1_rec, title = "Countries", reorder = TRUE, nudge_y = .03)

```



# Gender

Please select the gender category that best describes you

```{r e2, fig.width=6, fig.height=3}

answer_levels_e2 <- c("Man", "Woman", "Prefer not to say", "Other")

e2_df <- df %>% 
  select("E2")

e2_df_rec <- e2_df %>% 
  mutate(across(.fns = factor, levels = answer_levels_e2))


e2_df_rec %>% 
  plot_bar(E2, title = "Gender", reorder = TRUE, nudge_y = .079)
```


# Age cohorts

What is your age?

```{r e3, fig.width=7, fig.height=3.5}

answer_levels_e3 <- c("<20", "20-29", "30-39", "40-49", "50-59", "60-69", "70+")

e3_df <- df %>% 
  select("E3")

e3_df_rec <- e3_df %>% 
  mutate(across(.fns = factor, levels = answer_levels_e3))


e3_df_rec %>%
  mutate(across(.fns = as.numeric)) %>% 
  summarise(across(everything(), ~mean(.x, na.rm = TRUE)))

e3_df_rec %>%
  plot_bar(E3, title = "Age cohorts", reorder = FALSE, nudge_y = .028)

```

# Publish first academic publication

When did you publish your first academic publication (journal article, book, chapter, conference proceeding, or similar)? Please tell us the year.

```{r e3b, fig.width=6, fig.height=3}

e3b_df <- df %>% 
  select("E3b") %>% 
  filter(E3b > 1960)

e3b_df %>% 
  ggplot(aes(E3b)) +
  geom_histogram() +
  labs(x = NULL, y = NULL, title = NULL) +
  hrbrthemes::theme_ipsum(base_family = "Hind")

```


# Highest education

What is the highest education level you completed? [drop down]

```{r e4, fig.width=6, fig.height=3}
answer_levels_e4 <- c("Post-secondary non-tertiary education (e.g. VET Schools, schools of healthcare and nursing)", "Short-cycle tertiary education (e.g. master schools, colleges, vocational training schools)", "Bachelor or equivalent", "Master or equivalent", "Doctorate or equivalent", "Other")

answer_labels_e4 <- str_wrap(answer_levels_e4, 30)

e4_df <- df %>% 
  select("E4")

e4_df_rec <- e4_df %>% 
  mutate(across(.fns = factor, levels = answer_levels_e4, 
                labels = answer_labels_e4))

e4_df_rec %>%
  plot_bar(E4, title = "Highest education", reorder = FALSE, nudge_y = .2) +
  scale_y_continuous(breaks = c(0, .25, .5, .75, 1), 
                     labels = function(x) scales::percent(x, accuracy = 1))
```

# Types of institution

In what type of institution do you work? [drop down]

```{r e5, fig.width=7, fig.height=3}

answer_levels_e5 <- c("University", "Public research institute", "Private research institute", "Company", "Nonprofit", "Other")

e5_df <- df %>% 
  select("E5")

e5_df_rec <- e5_df %>% 
  mutate(across(.fns = factor, levels = answer_levels_e5))

e5_df_rec %>% 
  plot_bar(E5, title = "Types of institution", reorder = TRUE, nudge_y = .13)

```

# Position

What is your position? Choose all that apply

```{r e6, fig.width=8, fig.height=5}

answer_levels_e6 <- c("Junior Researcher", "Senior Researcher", "Ph.D. student", "Postdoctoral fellow/ researcher", "Assistant professor", 
                      "Associate professor", "Full professor", "Associate research scientist", "Instructor", "Lecturer", "Adjunct professor", 
                      "Technician or lab manager", "Core facility manager", "Other")

e6_df <- df %>% 
  select("E6")

e6_df_rec <- e6_df %>% 
  mutate(across(.fns = factor, levels = answer_levels_e6))

e6_df_rec %>% 
  plot_bar(E6, title = "Position", reorder = TRUE, nudge_y = .035)
```

# Respondents by disciplines

In which general area of knowledge do you work?

```{r e7, fig.width=8, fig.height=3}

answer_levels_e7 <- c("Natural Sciences", "Engineering and technology", "Medical and health sciences", "Agricultural and Veterinary sciences", 
                      "Social Sciences", "Humanities and the Arts")

e7_df <- df %>% 
  select("E7")

e7_df_rec <- e7_df %>% 
  mutate(across(.fns = factor, levels = answer_levels_e7))

e7_df_rec %>% 
  plot_bar(E7, title = "Respondents by disciplines", reorder = TRUE, nudge_y = .055)

```


# A1 Practices in OS

Please rate the following statements according to your practices regarding Open Science

```{r a1, fig.width=8, fig.height=4.5, results="asis"}

answer_levels <- c("Strongly disagree", "Disagree", "Neither agree nor disagree",
                   "Agree", "Strongly agree", 
                   "This topic is not relevant to my research", 
                   "Don’t know/ Don’t have enough information")


a1_df <- df %>% 
  select(starts_with("A1[")) 

a1_df_rec <- a1_df %>% 
  mutate(across(.fns = factor, levels = answer_levels))


recode_successful(a1_df, a1_df_rec)

visdat::vis_miss(a1_df_rec)


a1_df_rec %>% 
  plot_likert()
```


# A2 Own practices regarding Open Access publishing

Please rate the following statements according to your own practices regarding Open Access publishing.

```{r a2, fig.width=8, fig.height=4.5, results="asis"}

answer_levels_2 <- c("Never", "Rarely", "Sometimes",
                   "Often", "Always", "This topic is not relevant to my research", 
                   "Don’t know/ Don’t have enough information")


a2_df <- df %>% 
  select(starts_with("A2[")) 

a2_df_rec <- a2_df %>% 
  mutate(across(.fns = factor, levels = answer_levels_2))

a2_df_rec %>% 
  plot_likert(legend_rows = 1)
```


# A3 Own practices regarding Research Data Management

Please rate the following statements according to your own practices regarding Research Data Management.

```{r a3, fig.width=8, fig.height=4.5, results="asis"}

a3_df <- df %>% 
  select(starts_with("A3[")) 

a3_df_rec <- a3_df %>% 
  mutate(across(.fns = factor, levels = answer_levels_2))

a3_df_rec %>% 
  plot_likert(legend_rows = 1)
```


# A4 Practices regarding Reproducible Research

Please rate the following statements according to your practices regarding Reproducible Research

```{r a4, fig.width=8, fig.height=4.5, results="asis"}

a4_df <- df %>% 
  select(starts_with("A4[")) 

a4_df_rec <- a4_df %>% 
  mutate(across(.fns = factor, levels = answer_levels_2))

a4_df_rec %>% 
  plot_likert(legend_rows = 1)
```


# A5 Practices regarding Open Peer Review

Please rate the following statements according to your practices regarding Open Peer Review.

```{r a5, fig.width=8, fig.height=4.5, results="asis"}

answer_levels <- c("Strongly disagree", "Disagree", "Neither agree nor disagree",
                   "Agree", "Strongly agree", 
                   "This topic is not relevant to my research", 
                   "Don’t know/ Don’t have enough information")


a5_df <- df %>% 
  select(starts_with("A5[")) 

a5_df_rec <- a5_df %>% 
  mutate(across(.fns = factor, levels = answer_levels))

a5_df_rec %>% 
  plot_likert()
```


# A6 Practices regarding Open Source Software

Please rate the following statements according to your practices regarding Open Source Software.

```{r a6, fig.width=8, fig.height=4.5, results="asis"}

a6_df <- df %>% 
  select(starts_with("A6[")) 

a6_df_rec <- a6_df %>% 
  mutate(across(.fns = factor, levels = answer_levels_2))

a6_df_rec %>% 
  plot_likert(legend_rows = 1)
```


# A7 Practices regarding Licensing

Please rate the following statements according to your practices regarding Licensing.

```{r a7, fig.width=8, fig.height=4.5, results="asis"}

a7_df <- df %>% 
  select(starts_with("A7[")) 

a7_df_rec <- a7_df %>% 
  mutate(across(.fns = factor, levels = answer_levels))

a7_df_rec %>% 
  plot_likert()
```


# A8 Practices regarding Research Integrity

Please rate the following statements according to your practices regarding Research Integrity

```{r a8, fig.width=8, fig.height=4.5, results="asis"}

a8_df <- df %>% 
  select(starts_with("A8[")) 

a8_df_rec <- a8_df %>% 
  mutate(across(.fns = factor, levels = answer_levels_2))

a8_df_rec %>% 
  plot_likert(legend_rows = 1)
```


# A9 Practices regarding Citizen Science (information, consultation, public participation)

Please rate the following statements according to your practices regarding Citizen Science - consider all levels -information, consultation, public participation

```{r a9, fig.width=8, fig.height=4.5, results="asis"}

a9_df <- df %>% 
  select(starts_with("A9[")) 

a9_df_rec <- a9_df %>% 
  mutate(across(.fns = factor, levels = answer_levels))

a9_df_rec %>% 
  plot_likert()
```


# A10 Practices regarding Gender Issues

Please rate the following statements according to your practices regarding Gender issues

```{r a10, fig.width=8, fig.height=4.5, results="asis"}

a10_df <- df %>% 
  select(starts_with("A10[")) 

a10_df_rec <- a10_df %>% 
  mutate(across(.fns = factor, levels = answer_levels))

a10_df_rec %>% 
  plot_likert()
```

# Part B Training on OS topics

# B1 Attended Training Events

How many training events have you attended in these topics?

```{r b1, fig.height=5, fig.width=7, results="asis"}

answer_levels_b1 <- c("None", "1", "2", "3-5", "more than 5")


b1_df <- df %>% 
  select(starts_with("B1[")) 

b1_df_rec <- b1_df %>% 
  mutate(across(.fns = factor, levels = answer_levels_b1))


b1_df_rec %>% 
  plot_likert(center_for_likert = 1.5, legend_rows = 1)
```


# B3 Attended Different Types of Training Sessions

How often did you attend the following types of training sessions?

```{r b3, fig.width=7, fig.height=5, results="asis"}

answer_levels_b3 <- c("Never", "Once", "More than once")


b3_df <- df %>% 
  select(starts_with("B3[")) 

b3_df_rec <- b3_df %>% 
  mutate(across(.fns = factor, levels = answer_levels_b3))

b3_df_rec %>% 
  plot_likert(center_for_likert = 1.5, legend_rows = 1)
```


# B5 Hours of training

How many hours of training in total did you get?

```{r b5, fig.width=6, fig.height=3, results="asis"}
# answer_levels_b5 <- c("None", "1", "2", "3-5", "More than 5", "Other")
# # remove "none" category, since these people did not receive training at all
answer_levels_b5 <- c("1", "2", "3-5", "More than 5")

b5_df <- df %>% 
  select("B5")

b5_df_rec <- b5_df %>% 
  mutate(across(.fns = factor, levels = answer_levels_b5))

recode_successful(b5_df, b5_df_rec)


b5_df_rec %>% 
  plot_bar(B5, title = "Hours of training", reorder = FALSE, nudge_y = .09)
```


# B6 Attended Different Types of Training Sessions

Did the training you receive fulfill your needs?

```{r b6, fig.width=7, fig.height=5, results="asis"}

answer_levels_b6 <- c("I didn’t receive training", 
                      "I received adequate training", 
                      "I need more training")


b6_df <- df %>% 
  select(starts_with("B6[")) 

b6_df_rec <- b6_df %>% 
  mutate(across(.fns = factor, levels = answer_levels_b6))

b6_df_rec %>% 
  plot_likert(legend_rows = 1, centered = FALSE)
```


# B8 Attendance of first formal training in any Open Science topic

When did you attend your first formal training in any Open Science topic?

```{r b8, fig.width=5.5, fig.height=3, results="asis"}

answer_levels_b8 <- c("During doctoral studies", "As a researcher", "During a conference", "Other")

b8_df <- df %>% 
  select("B8")

b8_df_rec <- b8_df %>% 
  mutate(across(.fns = factor, levels = answer_levels_b8))

b8_df_rec %>% 
  filter(B8 != "Other") %>%
  plot_bar(B8, title = "Attendance of first formal training in any Open Science topic", reorder = FALSE, nudge_y = .15)
```


Most responses from the "Other" category mention that they never received any
training.

# B9 Provider of attended training sessions

Who provided the training sessions you attended? (choose all that apply)

```{r b9, fig.width=8, fig.height=5.7, results="asis"}

answer_levels_3 <- c("No", "Yes")

b9_df <- df %>% 
  select(starts_with("B9[")) 

b9_df_rec <- b9_df %>% 
  mutate(across(.fns = factor, levels = answer_levels_3))

b9_df_rec %>% 
  plot_likert(legend_rows = 1)
```


# B10 Preferred way to learn OS topics

What is your preferred way to learn open science topics? (choose all that apply)

```{r b10, fig.width=8, fig.height=4.5, results="asis"}

b10_df <- df %>% 
  select(starts_with("B10["))

b10_df_rec <- b10_df %>% 
  mutate(across(.fns = factor, levels = answer_levels_3))

b10_df_rec %>% 
  plot_likert(legend_rows = 1)
```


# B11 Has your awareness of open science practices increased after the training you attended?

Has your awareness of open science practices increased after the training you attended?

```{r b11, fig.width=8, fig.height=4, results="asis"}

answer_levels_4 <- c("Highly disagree", "Disagree",
                     "Neither agree nor disagree",
                     "Agree", "Highly agree")


b11_df <- df %>% 
  select(starts_with("B11[")) 

b11_df_rec <- b11_df %>% 
  mutate(across(.fns = factor, levels = answer_levels_4))

recode_successful(b11_df, b11_df_rec)

b11_df_rec %>% 
  plot_likert()
```


# B12 Share experience OS practices/tool with colleagues

Would you share your experience with open science practices and tools with colleagues?

```{r b12, fig.width=8, fig.height=4, results="asis"}

b12_df <- df %>% 
  select(starts_with("B12[")) 

b12_df_rec <- b12_df %>% 
  mutate(across(.fns = factor, levels = answer_levels_4))

b12_df_rec %>% 
  plot_likert()
```



# Further todos

- check out cases with weird first year of publication `df %>% filter(id %in% c(356, 420, 129))`