food stocks comparisons

pip install pandas numpy matplotlib yfinance seaborn

#pandas and NumPy imports
import pandas as pd
from pandas import Series,DataFrame
import numpy as np

# For Visualization
import matplotlib.pyplot as plt
import seaborn as sns
sns.set_style('whitegrid')
%matplotlib inline

import os #for files read/write
from datetime import datetime # For time stamps
import yfinance as yf #fetching the data stock
from __future__ import division# For division in Python 3

# Fetch stock data
def fetch_stock_data(ticker, start_date, end_date):
    stock_data = yf.download(ticker, start=start_date, end=end_date)
    return stock_data
smg_data = fetch_stock_data('SMGBF', '2021-01-01', '2023-12-31')
jbf_data = fetch_stock_data('JBFCY', '2021-01-01', '2023-12-31')
uvr_data = fetch_stock_data('UVRBF', '2021-01-01', '2023-12-31')
delm_data = fetch_stock_data('MDLZ', '2021-01-01', '2023-12-31')

print(smg_data.head())
print(jbf_data.head())
print(uvr_data.head())
print(delm_data.head())

print(smg_data.isnull().sum())
print(jbf_data.isnull().sum())
print(uvr_data.isnull().sum())
print(delm_data.isnull().sum())

type(smg_data) #I just like to check what type of data we are working with

path = 'fnbStocks.xlsx'
isExist = os.path.exists(path)
print(isExist)

display(smg_data)

display(smg_data.columns)

smg_data.columns= [col[0] for col in smg_data.columns]
jbf_data.columns=[col[0] for col in jbf_data.columns]
uvr_data.columns=[col[0] for col in uvr_data.columns]
delm_data.columns=[col[0] for col in delm_data.columns]

display(smg_data.columns)

display(smg_data)

with pd.ExcelWriter('fnbStocks.xlsx') as writer:
    smg_data.to_excel(writer, sheet_name='SanMiguel')
    jbf_data.to_excel(writer, sheet_name='Jollibee')
    uvr_data.to_excel(writer, sheet_name='Robina')
    delm_data.to_excel(writer, sheet_name='DelMonte')

smg_data['Volume'].plot(legend=True,figsize=(10,6))
#historical view of volume for San Miguel Corp

plt.figure(figsize=(10, 6))
sns.lineplot(x='Date', y='Volume', data=jbf_data, marker='o')
plt.xticks(rotation=45)
plt.title('Jollibee Foods Corps')
plt.xlabel('Volume over Year and Month')
plt.tight_layout()
plt.show()

display(uvr_data)

# Convert 'date_column' to datetime format
uvr_data = uvr_data.reset_index(drop=False)
display(uvr_data)

sns.set_theme(rc={'figure.figsize':(11.7,8.27)})
sns.lineplot(data=smg_data, x='Date', y='Close', label='San Miguel')
sns.lineplot(data=delm_data, x='Date', y='Close', label='Mondelez')
sns.lineplot(data=uvr_data, x='Date', y='Close', label='Robina')
sns.lineplot(data=jbf_data, x='Date', y='Close', label='Jabee')

smg_data = smg_data.reset_index(drop=False)
jbf_data = jbf_data.reset_index(drop=False)
delm_data = delm_data.reset_index(drop=False)

smg_data.insert(0, 'Name', 'San Miguel Corp')
jbf_data.insert(0, 'Name', 'Jollibee Food Corp')
delm_data.insert(0, 'Name', 'Mondelez International')
uvr_data.insert(0, 'Name', 'Universal Robina Corp')
#adding a columns Name in the data frame

# The comp stocks we'll use for this analysis
comp_list = [smg_data,jbf_data,uvr_data,delm_data]
#merging all the companies
comp_listGlobal = pd.concat(comp_list)

display(comp_listGlobal)

sns.lineplot(data=comp_listGlobal,x="Date", y="Close", hue="Name", style="Name")

#pivot a new data frame here
CloseDF = comp_listGlobal.pivot(index='Date', columns='Name', values=['Close'])
display(CloseDF)

# Calculate the daily return percent of all stocks and store them 
comp_returns = CloseDF.pct_change()

display(comp_returns)

sns.pairplot(comp_returns.dropna())
#correlation analysis for all possible pairs of stocks in our food stock ticker list.

# Mixed plot to visualize the correlation between all food stocks
comp_fig = sns.PairGrid(comp_returns.dropna())
comp_fig.map_upper(plt.scatter,color='green')
comp_fig.map_lower(sns.kdeplot,cmap='Purples_d')
comp_fig.map_diag(plt.hist,bins=30)

# Correlation plot for the daily returns of all stocks
comp_returns_corr= comp_returns.dropna().corr()
sns.heatmap(comp_returns_corr,annot=True)