import warnings; warnings.filterwarnings("ignore")

# Data setup: Load daily minimum temperature data
import pandas as pd
url = "https://raw.githubusercontent.com/jbrownlee/Datasets/master/daily-min-temperatures.csv"
df = pd.read_csv(url, parse_dates=["Date"])
print("Data shape:", df.shape)
df.head()

# Quick data check: Check for missing values
df.isnull().sum()

# Basic plot: Line chart of daily temperatures
import matplotlib.pyplot as plt
plt.figure(figsize=(10,4))
plt.plot(df["Date"], df["Temp"])
plt.title("Daily Minimum Temperatures")
plt.ylabel("Temperature (Celsius)")
plt.xlabel("Date")
plt.show()

# Quick mean and variance check
window = 365  # About a year
df["rolling_mean"] = df["Temp"].rolling(window).mean()
df["rolling_var"] = df["Temp"].rolling(window).var()
plt.figure(figsize=(10,4))
plt.plot(df["Date"], df["Temp"], label="Original")
plt.plot(df["Date"], df["rolling_mean"], label="Rolling Mean")
plt.plot(df["Date"], df["rolling_var"], label="Rolling Variance")
plt.legend()
plt.title("Rolling Mean and Variance")
plt.show()

# Run the Augmented Dickey-Fuller test
from statsmodels.tsa.stattools import adfuller
result = adfuller(df["Temp"])
print("ADF Statistic:", result[0])
print("p-value:", result[1])
for key, value in result[4].items():
    print("Critical Value ({}): {:.3f}".format(key, value))
    

# Print a human-friendly summary
if result[1] < 0.05:
    print("The series is likely stationary (p < 0.05)")
else:
    print("The series is likely not stationary (p >= 0.05)")
    

# Differencing to remove trend
df["diff_1"] = df["Temp"].diff()
plt.figure(figsize=(10,4))
plt.plot(df["Date"], df["diff_1"])
plt.title("First Difference of Temperature")
plt.show()

# Run ADF on differenced data
import numpy as np
diff_result = adfuller(df["diff_1"].dropna())
print("ADF Statistic (1st diff):", diff_result[0])
print("p-value:", diff_result[1])

# Seasonal differencing to remove seasonality effect
df["seasonal_diff"] = df["Temp"].diff(365)
plt.figure(figsize=(10,4))
plt.plot(df["Date"], df["seasonal_diff"])
plt.title("Seasonal Differencing (365 days)")
plt.show()

# Try ADF again with seasonal differencing
seasonal_result = adfuller(df["seasonal_diff"].dropna())
print("ADF Statistic (seasonal):", seasonal_result[0])
print("p-value:", seasonal_result[1])

# Apply a log transformation
df["log_temp"] = np.log(df["Temp"] + 1)
plt.figure(figsize=(10,4))
plt.plot(df["Date"], df["log_temp"])
plt.title("Log-Transformed Temperature")
plt.show()

# Combine: Log transform AND differencing
df["log_diff"] = df["log_temp"].diff()
plt.figure(figsize=(10,4))
plt.plot(df["Date"], df["log_diff"])
plt.title("First Difference of Log-Transformed Data")
plt.show()

# ADF test after all transformations
transformed_result = adfuller(df["log_diff"].dropna())
print("ADF Statistic (log diff):", transformed_result[0])
print("p-value:", transformed_result[1])

# Mini Project: Ask user for differencing period
period = int(input("Enter differencing period (e.g., 1 for day, 365 for year): "))
df["user_diff"] = df["Temp"].diff(period)
plt.figure(figsize=(10,4))
plt.plot(df["Date"], df["user_diff"], label="User Difference")
plt.title(f"Differencing with Period = {period}")
plt.legend()
plt.show()

# Extra: Try ADF test on user-differenced column
user_result = adfuller(df["user_diff"].dropna())
print("ADF Statistic (Your diff):", user_result[0])
print("p-value:", user_result[1])

# Challenge: Try with your own CSV file
file = input("Paste a CSV URL or path to your own time series: ")
try:
    new_df = pd.read_csv(file, parse_dates=True)
    print(new_df.head())
except Exception as e:
    print("Could not load your file. Please check the path and try again.")