import warnings; warnings.filterwarnings('ignore')
# Basic imports
import pandas as pd
import matplotlib.pyplot as plt

# These tools help you work with data and charts

# Data setup
url = 'https://raw.githubusercontent.com/jbrownlee/Datasets/master/shampoo.csv'
df = pd.read_csv(url)
print('Shape:', df.shape)
print(df.head())

# Let us look at a simple plot
plt.figure(figsize=(8,4))
plt.plot(df['Sales'])
plt.xlabel('Month')
plt.ylabel('Sales')
plt.title('Monthly Shampoo Sales')
plt.show()

# Checking if data has missing values
print(df.isnull().sum())

# Rename columns for easy access
df.columns = ['Month', 'Sales']
print(df.columns)

# Convert sales to numbers (sometimes CSV is not read as float)
df['Sales'] = pd.to_numeric(df['Sales'], errors='coerce')
print(df.dtypes)
print('Any missing?', df['Sales'].isnull().any())

# Add a column for previous month's sales (lag-1 feature)
df['Prev_Sales'] = df['Sales'].shift(1)
# Drop first row with missing lag value
df = df.dropna()
df.head()

# Splitting data for training and testing
from sklearn.model_selection import train_test_split
X = df[['Prev_Sales']]
y = df['Sales']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
print('Train samples:', len(X_train))
print('Test samples:', len(X_test))

# Fit the model
from sklearn.linear_model import LinearRegression
model = LinearRegression()
model.fit(X_train, y_train)
print('Model trained!')

# Predict sales using the model
y_pred = model.predict(X_test)
print('Predictions:', y_pred[:5])

# Measure how well the model works
from sklearn.metrics import mean_squared_error
mse = mean_squared_error(y_test, y_pred)
print('Mean Squared Error:', mse)

# Plot actual vs predicted values
plt.figure(figsize=(8,4))
plt.plot(y_test.values, label='Actual')
plt.plot(y_pred, label='Predicted')
plt.legend()
plt.title('Actual vs Predicted Sales')
plt.show()

# Challenge: Try a two-month lag
df['Prev_Sales_2'] = df['Sales'].shift(2)
df2 = df.dropna()
X2 = df2[['Prev_Sales', 'Prev_Sales_2']]
y2 = df2['Sales']
X2_train, X2_test, y2_train, y2_test = train_test_split(X2, y2, test_size=0.2, random_state=42)
model2 = LinearRegression()
model2.fit(X2_train, y2_train)
y2_pred = model2.predict(X2_test)
mse2 = mean_squared_error(y2_test, y2_pred)
print('MSE with two lags:', mse2)

# Mini project: Can you predict future sales based on user input?
input_prev = float(input('What was sales last month? '))
input_prev2 = float(input('And two months ago? '))
user_X = [[input_prev, input_prev2]]
user_pred = model2.predict(user_X)
print('Predicted sales next month:', user_pred[0])

# Troubleshooting: What if your data breaks?
try:
    fake_input = float(input('Test: Enter a word or wrong type: '))
except ValueError:
    print('Input could not be turned into a number. Please enter digits only.')