import pandas as pd
import matplotlib.pyplot as plt

import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline

import pandas as pd
import matplotlib.pyplot as plt

#import numpy and pandas package
import numpy as np
import pandas as pd

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

ms = pd.read_csv('data/microsoft.csv',index_col=0)
ms.index=pd.to_datetime(ms.index)
ms.head()

import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
# To recall, this is the code to mimic the roll dice game for 50 times

die = pd.DataFrame([1, 2, 3, 4, 5, 6])
trial = 50
results = [die.sample(2, replace=True).sum().loc[0] for i in range(trial)]
# This is the code for summarizing the results of sum of faces by frequency

freq = pd.DataFrame(results)[0].value_counts()
sort_freq = freq.sort_index()
print(sort_freq)

import pandas as pd
import numpy as np
from scipy.stats import norm
ms = pd.read_csv('data/microsoft.csv',index_col=0)
ms.index=pd.to_datetime(ms.index)
ms.head()

import pandas as pd
import numpy as np
from scipy.stats import norm
%matplotlib inline
# Sample mean and SD keep changing, but always within a certain range
Fstsample = pd.DataFrame(np.random.normal(10, 5, size=30))
print('sample mean is ', Fstsample[0].mean())
print('sample SD is ', Fstsample[0].std(ddof=1))

import pandas as pd
import numpy as np
# Create a Population DataFrame with 10 data 

data = pd.DataFrame()
data['Population'] = [47, 48, 85, 20, 19, 13, 72, 16, 50, 60]

import pandas as pd
import numpy as np
from scipy.stats import norm
import matplotlib.pyplot as plt
% matplotlib inline
# import microsoft.csv, and add a new feature - logreturn
ms = pd.read_csv('data/microsoft.csv',index_col=0)
ms.index=pd.to_datetime(ms.index)
ms['logReturn'] = np.log(ms['Close'].shift(-1)) - np.log(ms['Close'])
# Log return goes up and down during the period
ms['logReturn'].plot(figsize=(20, 8))
plt.axhline(0, color='red')
plt.show()