---
title: "Introduction to quickSentiment"
output: rmarkdown::html_vignette
vignette: >
  %\VignetteIndexEntry{Introduction to quickSentiment}
  %\VignetteEngine{knitr::rmarkdown}
  %\VignetteEncoding{UTF-8}
---

# --- 1. SETUP: LOAD LIBRARIES ---
# -------------------------------------------------------------------
```{r, include = FALSE}
library(quickSentiment)

```

```{r setup}
library(doParallel)
# CRAN limits the number of cores used during package checks
cores <- min(2, parallel::detectCores())
registerDoParallel(cores = cores)
```

# --- 2. LOAD AND PREPARE TRAINING DATA ---
```{r}
# Look for the file in the installed package first
csv_path <- system.file("extdata", "tweets.csv", package = "quickSentiment")

# Fallback for when you are building the package locally
if (csv_path == "") {
  csv_path <- "../inst/extdata/tweets.csv"
}
tweets <- read.csv(csv_path)
set.seed(123)
```

# --- 3. PREPROCESS THE TEXT ---
# -------------------------------------------------------------------
# Use the pre_process() function from our package to clean the raw text.
# This step is done externally to the main pipeline, allowing you to reuse
# the same cleaned text for multiple different models or analyses in the future.


```{r}
tweets$cleaned_text <- pre_process(tweets$Tweet)
tweets$sentiment = ifelse(tweets$Avg>0,'P','N')
```

# --- 4. RUN THE MAIN TRAINING PIPELINE ---
# -------------------------------------------------------------------
# This is the core of the package. We call the main pipeline() function
# to handle the train/test split, vectorization, model training, and evaluation.

```{r}
result <- pipeline(
  # --- Define the vectorization method ---
  # Options: "bow" (raw counts), "tf" (term frequency), "tfidf"
  vect_method = "tf",
  
  # --- Define the model to train ---
  # Options: "logit", "rf", "xgb"
  model_name = "rf",
  
  # --- Specify the data and column names ---
  df = tweets,
  text_column_name = "cleaned_text",      # The column with our preprocessed text
  sentiment_column_name = "sentiment",    # The column with the target variable
  
  # --- Set vectorization options ---
  # Use n_gram = 2 for unigrams + bigrams, or 1 for just unigrams
  n_gram = 1
)
```
# ===================================================================
# --- 5. PREDICTION ON NEW, UNSEEN DATA ---
# ===================================================================
# The training is complete. The 'result' object now contains our trained
# model and all the necessary "artifacts" for prediction.
```{r}

tweets$sentimentPredict <- prediction(
  pipeline_object = result,
  df = tweets,
  text_column = "cleaned_text"
)

```