import pandas as pd

import matplotlib.pyplot as plt

# Load the data (ensure the CSV has a 'Week' column for proper
parsing)
df = pd.read_csv("C:/Users/Tisha/Downloads/input.csv")

# Group by 'Round' and 'Week' to sum the required columns over the 5
days of each week for each round
weekly_sum = df.groupby(['Round', 'Week'])[['total order', 'demand of
retailer1', 'demand of retailer2']].sum().reset_index()

# Group by 'Week' to sum the values from both rounds

week_sum = weekly_sum.groupby('Week')[['total order', 'demand of
retailer1', 'demand of retailer2']].sum().reset_index()

# Set the index to 'Week' for plotting

week_sum.set_index('Week', inplace=True)

# Create subplots
fig, axs = plt.subplots(3, 1, figsize=(12, 18))

# Plot Total Order

axs[0].plot(week_sum.index, week_sum['total order'], marker='o',
linestyle='-', color='blue', linewidth=2)
axs[0].set_title('Total Order by Week', fontsize=16)
axs[0].set_ylabel('Total Order', fontsize=14)
axs[0].grid(True, linestyle='--', alpha=0.7)

# Plot Demand of Retailer 1

axs[1].plot(week_sum.index, week_sum['demand of retailer1'],
marker='s', linestyle='-', color='orange', linewidth=2)
axs[1].set_title('Demand of Retailer 1 by Week', fontsize=16)
axs[1].set_ylabel('Demand of Retailer 1', fontsize=14)
axs[1].grid(True, linestyle='--', alpha=0.7)

# Plot Demand of Retailer 2

axs[2].plot(week_sum.index, week_sum['demand of retailer2'],
marker='^', linestyle='-', color='green', linewidth=2)
axs[2].set_title('Demand of Retailer 2 by Week', fontsize=16)
axs[2].set_ylabel('Demand of Retailer 2', fontsize=14)
axs[2].grid(True, linestyle='--', alpha=0.7)

# Add x-label for the bottom subplot

axs[2].set_xlabel('Week', fontsize=14)

# Adjust layout
plt.tight_layout()
plt.show()
# Define target variables for demand1, demand2, and total orders
target_retailer1 = week_sum['demand of retailer1']
target_retailer2 = week_sum['demand of retailer2']
target_total_orders = week_sum['total order']

from statsmodels.tsa.stattools import adfuller

# Define target variables in a dictionary
targets = {
'Retailer 1 Demand': target_retailer1,
'Retailer 2 Demand': target_retailer2,
'Total Orders': target_total_orders
}

# Loop through each target variable and perform the ADF test
for name, target in targets.items():
result = adfuller(target)
print(f'ADF Statistic for {name}: {result[0]}')
print(f'p-value for {name}: {result[1]}')

if result[1] < 0.05:

print(f"{name} is stationary, no differencing required (d=0)\
n")
else:
print(f"{name} is non-stationary, differencing required\n")
ADF Statistic for Retailer 1 Demand: -23.28378425677077
p-value for Retailer 1 Demand: 0.0
Retailer 1 Demand is stationary, no differencing required (d=0)

ADF Statistic for Retailer 2 Demand: -22.663477107633145

p-value for Retailer 2 Demand: 0.0
Retailer 2 Demand is stationary, no differencing required (d=0)

ADF Statistic for Total Orders: -21.601422151622316

p-value for Total Orders: 0.0
Total Orders is stationary, no differencing required (d=0)

# Step 3: Seasonal Decomposition to check for seasonality

decomposition = sm.tsa.seasonal_decompose(df['total order'],
model='additive', period=52) # Change period if needed
decomposition.plot()
plt.show()

# Step 3: Seasonal Decomposition to check for seasonality

decomposition = sm.tsa.seasonal_decompose(df['demand of retailer1'],
model='additive', period=52) # Change period if needed
decomposition.plot()
plt.show()

# Step 3: Seasonal Decomposition to check for seasonality

decomposition = sm.tsa.seasonal_decompose(df['demand of retailer2'],
model='additive', period=52) # Change period if needed
decomposition.plot()
plt.show()
import pmdarima as pm
import pandas as pd

# Step 2: Load your data

df = pd.read_csv("C:/Users/Tisha/Downloads/input.csv")

# Fit auto_arima while fixing d=0

model = pm.auto_arima(df['demand of retailer1'], d=0, start_p=0,
start_q=0,
max_p=5, max_q=5, seasonal=False, trace=True,
error_action='ignore', suppress_warnings=True)

# Print the best ARIMA order and AIC

print(f"Selected ARIMA order: {model.order}")
print(f"Model AIC: {model.aic()}")

Performing stepwise search to minimize aic

ARIMA(0,0,0)(0,0,0)[0] : AIC=447846.238, Time=0.17 sec
ARIMA(1,0,0)(0,0,0)[0] : AIC=inf, Time=0.22 sec
ARIMA(0,0,1)(0,0,0)[0] : AIC=402118.685, Time=1.43 sec
ARIMA(1,0,1)(0,0,0)[0] : AIC=286051.205, Time=0.33 sec
ARIMA(2,0,1)(0,0,0)[0] : AIC=285536.498, Time=2.97 sec
ARIMA(2,0,0)(0,0,0)[0] : AIC=inf, Time=0.28 sec
ARIMA(3,0,1)(0,0,0)[0] : AIC=285307.770, Time=7.47 sec
ARIMA(3,0,0)(0,0,0)[0] : AIC=inf, Time=0.37 sec
ARIMA(4,0,1)(0,0,0)[0] : AIC=284918.782, Time=8.09 sec
ARIMA(4,0,0)(0,0,0)[0] : AIC=inf, Time=0.44 sec
ARIMA(5,0,1)(0,0,0)[0] : AIC=283712.465, Time=8.09 sec
ARIMA(5,0,0)(0,0,0)[0] : AIC=inf, Time=0.72 sec
ARIMA(5,0,2)(0,0,0)[0] : AIC=inf, Time=15.76 sec
ARIMA(4,0,2)(0,0,0)[0] : AIC=inf, Time=18.86 sec
ARIMA(5,0,1)(0,0,0)[0] intercept : AIC=275992.928, Time=31.50 sec
ARIMA(4,0,1)(0,0,0)[0] intercept : AIC=280104.226, Time=19.68 sec
ARIMA(5,0,0)(0,0,0)[0] intercept : AIC=279202.615, Time=2.61 sec
ARIMA(5,0,2)(0,0,0)[0] intercept : AIC=inf, Time=30.32 sec
ARIMA(4,0,0)(0,0,0)[0] intercept : AIC=280270.819, Time=1.92 sec
ARIMA(4,0,2)(0,0,0)[0] intercept : AIC=inf, Time=24.76 sec

Best model: ARIMA(5,0,1)(0,0,0)[0] intercept

Total fit time: 175.995 seconds
Selected ARIMA order: (5, 0, 1)
Model AIC: 275992.9278466774

import pmdarima as pm
import pandas as pd

# Step 2: Load your data

df = pd.read_csv("C:/Users/Tisha/Downloads/input.csv")

# Fit auto_arima while fixing d=0

model = pm.auto_arima(df['demand of retailer2'], d=0, start_p=0,
start_q=0,
max_p=5, max_q=5, seasonal=False, trace=True,
error_action='ignore', suppress_warnings=True)

# Print the best ARIMA order and AIC

print(f"Selected ARIMA order: {model.order}")
print(f"Model AIC: {model.aic()}")

Performing stepwise search to minimize aic

ARIMA(0,0,0)(0,0,0)[0] : AIC=447648.671, Time=0.16 sec
ARIMA(1,0,0)(0,0,0)[0] : AIC=inf, Time=0.19 sec
ARIMA(0,0,1)(0,0,0)[0] : AIC=401945.322, Time=1.47 sec
ARIMA(1,0,1)(0,0,0)[0] : AIC=286663.201, Time=0.50 sec
ARIMA(2,0,1)(0,0,0)[0] : AIC=inf, Time=8.90 sec
ARIMA(1,0,2)(0,0,0)[0] : AIC=286664.582, Time=0.80 sec
ARIMA(0,0,2)(0,0,0)[0] : AIC=inf, Time=8.27 sec
ARIMA(2,0,0)(0,0,0)[0] : AIC=inf, Time=0.29 sec
ARIMA(2,0,2)(0,0,0)[0] : AIC=inf, Time=10.57 sec
ARIMA(1,0,1)(0,0,0)[0] intercept : AIC=282357.303, Time=5.60 sec
ARIMA(0,0,1)(0,0,0)[0] intercept : AIC=299217.741, Time=2.64 sec
ARIMA(1,0,0)(0,0,0)[0] intercept : AIC=282727.743, Time=0.89 sec
ARIMA(2,0,1)(0,0,0)[0] intercept : AIC=281415.847, Time=15.99 sec
ARIMA(2,0,0)(0,0,0)[0] intercept : AIC=282248.654, Time=1.24 sec
ARIMA(3,0,1)(0,0,0)[0] intercept : AIC=281124.276, Time=16.75 sec
ARIMA(3,0,0)(0,0,0)[0] intercept : AIC=281641.498, Time=1.62 sec
ARIMA(4,0,1)(0,0,0)[0] intercept : AIC=280674.617, Time=23.21 sec
ARIMA(4,0,0)(0,0,0)[0] intercept : AIC=280846.494, Time=1.82 sec
ARIMA(5,0,1)(0,0,0)[0] intercept : AIC=276592.958, Time=26.55 sec
ARIMA(5,0,0)(0,0,0)[0] intercept : AIC=279760.865, Time=2.41 sec
ARIMA(5,0,2)(0,0,0)[0] intercept : AIC=inf, Time=31.93 sec
ARIMA(4,0,2)(0,0,0)[0] intercept : AIC=inf, Time=27.74 sec
ARIMA(5,0,1)(0,0,0)[0] : AIC=284362.558, Time=8.90 sec

Best model: ARIMA(5,0,1)(0,0,0)[0] intercept

Total fit time: 198.442 seconds
Selected ARIMA order: (5, 0, 1)
Model AIC: 276592.95830631914

import pmdarima as pm
import pandas as pd

# Step 2: Load your data

df = pd.read_csv("C:/Users/Tisha/Downloads/input.csv")

# Fit auto_arima while fixing d=0

model = pm.auto_arima(df['total order'], d=0, start_p=0, start_q=0,
max_p=5, max_q=5, seasonal=False, trace=True,
error_action='ignore', suppress_warnings=True)

# Print the best ARIMA order and AIC

print(f"Selected ARIMA order: {model.order}")
print(f"Model AIC: {model.aic()}")

Performing stepwise search to minimize aic

ARIMA(0,0,0)(0,0,0)[0] : AIC=502611.463, Time=0.16 sec
ARIMA(1,0,0)(0,0,0)[0] : AIC=inf, Time=0.20 sec
ARIMA(0,0,1)(0,0,0)[0] : AIC=452613.367, Time=1.49 sec
ARIMA(1,0,1)(0,0,0)[0] : AIC=277446.101, Time=0.25 sec
ARIMA(2,0,1)(0,0,0)[0] : AIC=276909.832, Time=3.17 sec
ARIMA(2,0,0)(0,0,0)[0] : AIC=inf, Time=0.30 sec
ARIMA(3,0,1)(0,0,0)[0] : AIC=276733.492, Time=3.57 sec
ARIMA(3,0,0)(0,0,0)[0] : AIC=inf, Time=0.35 sec
ARIMA(4,0,1)(0,0,0)[0] : AIC=276325.169, Time=4.53 sec
ARIMA(4,0,0)(0,0,0)[0] : AIC=inf, Time=0.45 sec
ARIMA(5,0,1)(0,0,0)[0] : AIC=275183.672, Time=9.63 sec
ARIMA(5,0,0)(0,0,0)[0] : AIC=inf, Time=1.17 sec
ARIMA(5,0,2)(0,0,0)[0] : AIC=inf, Time=13.07 sec
ARIMA(4,0,2)(0,0,0)[0] : AIC=inf, Time=9.66 sec
ARIMA(5,0,1)(0,0,0)[0] intercept : AIC=268303.806, Time=27.48 sec
ARIMA(4,0,1)(0,0,0)[0] intercept : AIC=271334.758, Time=30.11 sec
ARIMA(5,0,0)(0,0,0)[0] intercept : AIC=270426.505, Time=2.53 sec
ARIMA(5,0,2)(0,0,0)[0] intercept : AIC=inf, Time=31.38 sec
ARIMA(4,0,0)(0,0,0)[0] intercept : AIC=271506.843, Time=1.86 sec
ARIMA(4,0,2)(0,0,0)[0] intercept : AIC=inf, Time=26.60 sec

Best model: ARIMA(5,0,1)(0,0,0)[0] intercept

Total fit time: 167.941 seconds
Selected ARIMA order: (5, 0, 1)
Model AIC: 268303.8063647584