Amazon Stock Price Analysis in Python

Step:1

First, we import necessary librates

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
import seaborn as sns

from sklearn.metrics import mean_squared_error

from statsmodels.graphics.tsaplots import plot_acf
from statsmodels.tsa.ar_model import AR
from statsmodels.tsa.arima_model import ARIMA
from statsmodels.tsa.arima_model import ARMA

Step:2
Then we will upload the dataset of Amazon_Dataset

Amazon_Data = pd.read_csv('Amazon_Dataset.csv')
Amazon_Data

Step:3

Now we will do basic data exploration

head(): This helps to see a few sample rows of the data

Amazon_Data.head()

describe(): This provides the summarized information of the data

Amazon_Data.describe()

Step:4

Now we look at  Data and Close column together

t=Amazon_Data['Date']
t

t.head()

c=Amazon_Data['Close']
c.head()

new=pd.concat([t,c],axis=1)
new.head()

Y = Amazon.values
size = int(len(Y) * 0.70)  # 70 % 
# Training set
train = Y[:size]
# testing set
test  = Y[size:len(Y)]

print("Total Samples    : %d" % len(Y))
print("Training Samples : %d" % len(train))
print("Testing Samples  : %d" % len(test))

Step:5

Plotting Scatter v/s Density

def plotScatterMatrix(Amazon_Data, plotSize, textSize):
    Amazon_Data = Amazon_Data.select_dtypes(include =[np.number]) 
    Amazon_Data = Amazon_Data.dropna('columns')
    Amazon_Data = Amazon_Data[[col for col in Amazon_Data if Amazon_Data[col].nunique() > 1]]
    columnNames = list(Amazon_Data)
    if len(columnNames) > 10: 
        columnNames = columnNames[:10]
    Amazon_Data = Amazon_Data[columnNames]
    ax = pd.plotting.scatter_matrix(Amazon_Data, alpha=0.2, figsize=[plotSize, plotSize], diagonal='density')
    corrs = Amazon_Data.corr().values
    for p, q in zip(*plt.np.triu_indices_from(ax, k = 1)):
        ax[p, q].annotate('Corr. coef = %.2f' % corrs[p, q], (0.8, 0.2), xycoords='axes fraction', ha='center', va='bottom', size=textSize)
    plt.plot(Amazon.Date, marker= '+', markersize =2, markerfacecolor= 'green', markeredgecolor= 'black')
    plt.show()

plotScatterMatrix(Amazon_Data, 18, 10)

Step:6

Now we keep only the close column and see the last five-year closing stock price

# Keep only 'Close' column
Amazon = Amazon_Data.drop(['Open', 'High', 'Low', 'Adj Close', 'Volume'], axis=1)

Amazon = Amazon[Amazon['Date'] >='2015-01-01']

plt.figure(figsize=(10, 5))
plt.title('Amazon stock closing prices for last 5 years', fontsize=14)
plt.plot(Amazon.Close, marker= '+', markersize =2, markerfacecolor= 'green', markeredgecolor= 'red')

So we calculate the last five year mean and variance price

Q1_2019_mean = Amazon[(Amazon['Date'] >= '2019-01-01') & (Amazon['Date'] < '2019-03-31')].mean()
Q1_2019_var  = Amazon[(Amazon['Date'] >= '2019-01-01') & (Amazon['Date'] < '2019-03-31')].var()
Q2_2017_mean = Amazon[(Amazon['Date'] >= '2017-01-01') & (Amazon['Date'] < '2017-03-31')].mean()
Q2_2017_var  = Amazon[(Amazon['Date'] >= '2017-01-01') & (Amazon['Date'] < '2017-03-31')].var()
Q3_2015_mean = Amazon[(Amazon['Date'] >= '2015-10-01') & (Amazon['Date'] < '2015-12-31')].mean()
Q3_2015_var  = Amazon[(Amazon['Date'] >= '2015-10-01') & (Amazon['Date']< '2015-12-31')].var()



print('2019 Quarter 1 closing price mean    : %.2f ' % (Q1_2019_mean))
print('2019 Quarter 1 closing price variance : %.2f ' % (Q1_2019_var))
print("---------------------------------------------- ")
print('2017 Quarter 2 closing price mean     : %.2f ' % (Q2_2017_mean))
print('2017 Quarter 2 closing price variance : %.2f ' % (Q2_2017_var))
print("---------------------------------------------- ")
print('2015 Quarter 3 closing price mean     : %.2f ' % (Q3_2015_mean))
print('2015 Quarter 3 closing price variance : %.2f ' % (Q3_2015_var))

Here we calculate the closing mean price and variance and see the stock price increases in the last five years