In [1]:
# import packages for analysis and modeling
import pandas as pd #data frame operations
import numpy as np #arrays and math functions
from scipy.stats import uniform #for training and test splits
import statsmodels.api as smf #R-like model specification
import matplotlib.pyplot as plt #2D plotting
In [5]:
# read in Coaches data and create data frame
Coaches = pd.read_excel("coaches_modify.xlsx")
print(pd.DataFrame.head(Coaches))
In [6]:
Coaches.describe()
Out[6]:
In [4]:
# System Information
import platform
print('Python is ' + platform.python_version())
pd.show_versions(as_json=False)
In [7]:
Coaches.hist()
Out[7]:
In [12]:
Coaches['TotalPay'].hist()
plt.xticks(rotation='vertical')
Out[12]:
In [11]:
p = plt.hist(Coaches['TotalPay'])
plt.xticks(rotation='vertical')
plt.show()
In [14]:
import seaborn as sns # PROVIDES TRELLIS AND SMALL MULTIPLE PLOTTING
sns.boxplot(y="TotalPay", data=Coaches)
plt.show()
In [17]:
sns.boxplot(x="Conf", y="TotalPay", data=Coaches, color = "gray");
plt.xticks(rotation="vertical")
plt.show()
In [23]:
sns.scatterplot(x="W", y="TotalPay", hue="Conf", data=Coaches)
Out[23]:
In [24]:
sns.scatterplot(x="L", y="TotalPay", hue="Conf", data=Coaches)
Out[24]:
In [26]:
sns.regplot(x="W", y="TotalPay", data=Coaches);
In [27]:
sns.regplot(x="L", y="TotalPay", data=Coaches);
In [30]:
sns.lmplot(x="W", y="TotalPay", col="Conf", col_wrap=3, data=Coaches);
In [ ]: