sachinsdate

import pandas as pd
import numpy as np
import statsmodels.formula.api as smf
from statsmodels.api import add_constant
from statsmodels.sandbox.regression.gmm import IV2SLS


#Load the Panel Study of Income Dynamics (PSID) into a Dataframe
df = pd.read_csv('PSID1976.csv', header=0)

sachinsdate

import pandas as pd
from patsy import dmatrices
import numpy as np
import statsmodels.api as sm
import statsmodels.formula.api as smf
import statsmodels.stats.stattools as st
import matplotlib.pyplot as plt

#create a pandas DataFrame for the counts data set
df = pd.read_csv('bike_sharing_dataset_daywise.csv', header=0, parse_dates=['dteday'], infer_datetime_format=True)

sachinsdate

import pandas as pd
import numpy as np
import math
from matplotlib import pyplot as plt


#construct the date parser
mydateparser = lambda x: pd.datetime.strptime(x, '%d-%m-%y')

#load the data set into a pandas data frame

sachinsdate

import pandas as pd
from matplotlib import pyplot as plt
from statsmodels.tsa.holtwinters import ExponentialSmoothing as HWES

#read the data file. the date column is expected to be in the mm-dd-yyyy format.
df = pd.read_csv('retail_sales_used_car_dealers_us_1992_2020.csv', header=0, infer_datetime_format=True, parse_dates=[0], index_col=[0])
df.index.freq = 'MS'

#plot the data
df.plot()

sachinsdate

import pandas as pd
from matplotlib import pyplot as plt
from statsmodels.regression.linear_model import OLS as OLS
import statsmodels.api as sm


df = pd.read_csv('taiwan_real_estate_valuation_curated.csv', header=0)

y = df['HOUSE_PRICE_PER_UNIT_AREA']
X = df['HOUSE_AGE_YEARS']

sachinsdate

Sample_ID,Sample_Date,Beach_Name,Sample_Location,Enterococci_Results,Units_or_Notes
050514CP13,05/05/2014,MIDLAND BEACH,Center,20.0,MPN/100 ml
062011GR04,06/20/2011,MANHATTAN BEACH,Left,,Result below detection limit
072808BH09,07/28/2008,MIDLAND BEACH,Right,28.0,MPN/100 ml
051214CP36,05/12/2014,SOUTH BEACH,Right,4.0,MPN/100 ml
081511KB07,08/15/2011,CEDAR GROVE,Left,360.0,MPN/100 ml
062909KB01,06/29/2009,MANHATTAN BEACH,Left,8.0,MPN/100 ml
082112KB07,08/21/2012,CEDAR GROVE,Left,20.0,MPN/100 ml
072015GR06,07/20/2015,MANHATTAN BEACH,Right,,Result below detection limit
082613CP16,08/26/2013,SOUTH BEACH,Center,12.0,MPN/100 ml

sachinsdate

import math
import matplotlib.pyplot as plt
from scipy.stats import invweibull
from scipy.stats import norm
import numpy as np
import pandas as pd


#Load the data file
df = pd.read_csv('DOHMH_Beach_Water_Quality_Data.csv', header=0, infer_datetime_format=True, parse_dates=['Sample_Date'])

sachinsdate

import math
import numpy as np
import statsmodels.api as sm
from statsmodels.base.model import GenericLikelihoodModel
from scipy.stats import poisson
from scipy.stats import binom
from patsy import dmatrices
import statsmodels.graphics.tsaplots as tsa
from matplotlib import pyplot as plt

sachinsdate

import numpy as np
from matplotlib import pyplot as plt
import random
import math

#initialize the transition matrix P
P=np.array([[0.6,0.4],[0.75,0.25]])
#initialize pi_0
pi_0=np.array([0.5, 0.5])

sachinsdate

import pandas as pd
import numpy as np
from matplotlib import pyplot as plt
import statsmodels.api as sm

#Load the PCE and UMCSENT datasets
df = pd.read_csv(filepath_or_buffer='UMCSENT_PCE.csv', header=0, index_col=0,
                 infer_datetime_format=True, parse_dates=['DATE'])
#Set the index frequency to 'Month-Start'
df = df.asfreq('MS')