# Importing Necessay Python libraries


import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import plotly.graph_objs as go
import plotly.express as px
import plotly.io as pio
pio.templates.default = "plotly_white"
from statsmodels.tsa.arima.model import ARIMA
from statsmodels.graphics.tsaplots import plot_acf, plot_pacf

# reading the data
data = pd.read_csv('Netflix-Subscriptions.csv')
print(data.head())



data['Time Period'] = pd.to_datetime(data['Time Period'],
                                     format='%d/%m/%Y')
print(data.head())


fig = go.Figure()
fig.add_trace(go.Scatter(x=data['Time Period'],
                         y=data['Subscribers'],
                         mode='lines', name='Subscribers'))
fig.update_layout(title='Netflix Quarterly Subscriptions Growth',
                  xaxis_title='Date',
                  yaxis_title='Netflix Subscriptions')
fig.show()


data['Quarterly Growth Rate'] = data['Subscribers'].pct_change() * 100


data.head()

data["Bar Color"] = data["Quarterly Growth Rate"].apply(lambda x: 'green ' if x>0 else 'red')


fig = go.Figure()
fig.add_trace(go.Bar(
    x=data['Time Period'],
    y=data['Quarterly Growth Rate'],
    marker_color=data['Bar Color'],
    name='Quarterly Growth Rate'
))
fig.update_layout(title='Netflix Quarterly Subscriptions Growth Rate',
                  xaxis_title='Time Period',
                  yaxis_title='Quarterly Growth Rate (%)')
fig.show()


data["Year"] = data["Time Period"].dt.year

yearly_growth = data.groupby('Year')['Subscribers'].pct_change().fillna(0) * 100



# Create a new column for bar color (green for positive growth, red for negative growth)
data['Bar Color'] = yearly_growth.apply(lambda x: 'green' if x > 0 else 'red')

# Plot the yearly subscriber growth rate using bar graphs
fig = go.Figure()
fig.add_trace(go.Bar(
    x=data['Year'],
    y=yearly_growth,
    marker_color=data['Bar Color'],
    name='Yearly Growth Rate'
))
fig.update_layout(title='Netflix Yearly Subscriber Growth Rate',
                  xaxis_title='Year',
                  yaxis_title='Yearly Growth Rate (%)')
fig.show()



time_series = data.set_index('Time Period')['Subscribers']


differenced_series = time_series.diff().dropna()

# Plot ACF and PACF of differenced time series
fig, axes = plt.subplots(1, 2, figsize=(12, 4))
plot_acf(differenced_series, ax=axes[0])
plot_pacf(differenced_series, ax=axes[1])
plt.show()


p, d, q = 1, 1, 2
model = ARIMA(time_series, order=(p, d, q))
results = model.fit()
print(results.summary())


future_steps = 20
predictions = results.predict(len(time_series), len(time_series) + future_steps - 2)
predictions = predictions.astype(int)
predictions

# Create a DataFrame with the original data and predictions
forecast = pd.DataFrame({'Original': time_series, 'Predictions': predictions})

# Plot the original data and predictions
fig = go.Figure()

fig.add_trace(go.Scatter(x=forecast.index, y=forecast['Predictions'],
                         mode='lines', name='Predictions'))

fig.add_trace(go.Scatter(x=forecast.index, y=forecast['Original'],
                         mode='lines', name='Original Data'))

fig.update_layout(title='Netflix Quarterly Subscription Predictions',
                  xaxis_title='Time Period',
                  yaxis_title='Subscribers',
                  legend=dict(x=0.1, y=0.9),
                  showlegend=True)

fig.show()


forecast