import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
sns.set(color_codes =True)
%matplotlib inline
import statsmodels.api as sm
from scipy import stats
from scipy.stats import ttest_1samp, ttest_ind,mannwhitneyu,levene,shapiro,wilcoxon
SLADT=pd.read_excel("F:/2019 GB Python/SLA1t.xlsx")
SLADT
# 95% - Standard SLA
stats.ttest_1samp(SLADT.SLA,95)
# P value > 0.05 ---> Accept the Null Hypo
stats.normaltest(SLADT.SLA).pvalue
TDT=pd.read_excel("F:/2019 GB Python/2tandpairedt.xlsx")
TDT
TWOTDT=TDT[['Pre', 'Post']]
TWOTDT
sns.boxplot(x='variable', y='value', data = pd.melt(TWOTDT), width =0.3)
t_statistic, p_value = ttest_ind(TWOTDT.Pre, TWOTDT.Post)
print(t_statistic, p_value )
stats.normaltest(TWOTDT.Pre).pvalue
stats.normaltest(TWOTDT.Post).pvalue
levene(TWOTDT.Pre,TWOTDT.Post)
PAIRTDT= TDT[['Beforecoaching', 'Aftercoaching']]
PAIRTDT
sns.boxplot(x="variable", y="value", data=pd.melt(PAIRTDT),width=0.3)
stats.normaltest(TDT.Beforecoaching).pvalue
stats.normaltest(TDT.Aftercoaching).pvalue
stats.ttest_rel(TDT.Beforecoaching, TDT.Aftercoaching)
AN=pd.read_excel("F:/2019 GB Python/ANOVA.xlsx")
AN
ANS=AN.stack().rename_axis(('Series', 'Timing')).reset_index(name='Val')
ANS
sns.boxplot(x=ANS.Timing, y=ANS.Val, width=0.3)
stats.normaltest(ANS.Val).pvalue
from statsmodels.formula.api import ols
from statsmodels.stats.anova import anova_lm
y=ANS.Val
X=ANS.Timing
formula='y ~ X'
model = ols(formula, ANS).fit()
aov_table = anova_lm(model)
print(aov_table)