from llm4time.core.data import loader
from llm4time.core.evaluate import Statistics

# Data loading using CSV, XLSX, JSON or Parquet
df = loader.load_data("etth2.csv")

# Descriptive statistics
stats = Statistics(df['OT'])
print(f"Mean: {stats.mean}")
print(f"Median: {stats.median}")
print(f"1° Quartile: {stats.first_quartile}")
print(f"3° Quartile: {stats.third_quartile}")
print(f"Standard Deviation: {stats.std}")
print(f"Minimum: {stats.min}")
print(f"Maximum: {stats.max}")
print(f"Number of missing values: {stats.missing_count}")
print(f"Percentage of missing values: {stats.missing_percentage}")

from llm4time.core.data import preprocessor

# Standardize into time series format
df = preprocessor.standardize(
  df,
  date_col='date',    # Column containing dates/timestamps
  value_col='OT',     # Column containing time series values
  duplicates='first'  # How to handle duplicate rows: 'first' keeps the first occurrence
)

# Ensure all timestamps are present
df = preprocessor.normalize(df, freq='h')

from llm4time.core.data import imputation

# Replace missing values with the column mean
df = imputation.mean(df)

from llm4time.core.data import preprocessor

# Split the dataset into training and validation sets
train, y_val = preprocessor.split(
  df,
  start_date='2016-06-01 00:00:00', # Start of the training set
  end_date='2016-12-01 00:00:00',   # End of the training set
  periods=24                        # Number of periods to forecast
)

from llm4time.core import prompt
from llm4time.core import PromptType, TSFormat, TSType

content = prompt.generate(
    train,       # Training set [(date, value), ...]
    periods=24,  # Number of periods to forecast
    prompt_type=PromptType.ZERO_SHOT,  # prompt type: ZERO_SHOT (no examples)
    ts_format=TSFormat.ARRAY,          # time series format
    ts_type=TSType.NUMERIC             # Type of encoding for series values
)

from llm4time.core.models import OpenAI

model = OpenAI(
  model='gpt-4o',  # OpenAI model to be used.
  api_key='...',   # API key for authentication with the OpenAI service.
  base_url='..'    # Base URL of the OpenAI endpoint.
)

# Forecasting
response, prompt_tokens, response_tokens, time_sec = model.predict(
    content,          # Previously generated prompt
    temperature=0.7,  # Level of randomness in the response
    max_tokens=1000   # Maximum number of tokens in the response
)

print("Model response:", response)
print("Prompt tokens:", prompt_tokens)
print("Response tokens:", response_tokens)
print("Execution time (s):", time_sec)

from llm4time.core import formatter
from llm4time.core.evaluate.metrics import Metrics

# Converts the response string into a numerical list
y_pred = formatter.parse(
  response,
  ts_format=TSFormat.ARRAY,
  ts_type=TSType.NUMERIC
)

metrics = Metrics(y_val, y_pred)

# Error metrics
print(f"sMAPE: {metrics.smape}") # Symmetric Mean Absolute Percentage Error
print(f"MAE: {metrics.mae}")     # Mean Absolute Error
print(f"RMSE: {metrics.rmse}")   # Root Mean Squared Error

from llm4time.visualization import plots

# Generate a comparison plot between actual and predicted values
plots.plot_forecast("Comparison between actual and predicted values", y_val, y_pred)

# Generate a bar chart comparing descriptive statistics
plots.plot_forecast_statistics("Statistical comparison", y_val, y_pred)