# Import libraries and DataFrame # import numpy as np import matplotlib.pyplot as plt import pandas as pd from pandas import DataFrame, Series

# Read the data from pokeman.csv into a DataFrame using pandas read_csv() # Print out the first 6 lines of data using .head df = pd.read_csv ('pokeman.csv') df.head(6)

# print out the data types of all features using .dtypes (no parentheses) df.dtypes

# print out the column names using .columns df.columns

# Create a pandas Series for the feature Speed; print out type df['Speed']

# Create a NumPy array for the feature Speed (use.values) ; print out type sp= df.Speed.values print (type(sp)) print (sp)

# Make 1D NumPy arrays from the features Attack and Defense and do a scatter plot # using matplotlib # a= df.Attack.values d= df.Defense.values plt.plot (a, d, 'mo') plt.xlabel ('Attack') plt.ylabel ('Defense')

# Create a new DataFrame "df_mod" which is same as original but we drop "Type 2" feature; print out to check df_mod= df.drop (columns=[ 'Type 2']) df_mod

# Import libraries and DataFrame # import numpy as np import matplotlib.pyplot as plt import pandas as pd from pandas import DataFrame, Series import seaborn as sns

# Read the data into a DataFrame # Print out the first 5 lines of data df = pd.read_csv ('pokeman.csv') df.head(5)

# Add a white grid to the background of Seaborn plots using set_style sns.set_style ('whitegrid')

# Make a scatter plot using Seaborn's relplot of Defense statistics (y-axis) # vs Attacks Stats sns.relplot (x= 'Attack', y= 'Defense' , data=df)

# Repeat plot in previous cell but use color to indicate Type 1 (hue = ) sns.relplot (x= 'Attack', y= 'Defense' , data=df, hue = 'Type 1')

# Make a category plot of Defense statistics vs Type 1 (non-numerical) # Rotation labels on x-axis for readability using plt.xticks using plt.xticks(rotation=-45) sns.catplot (x= 'Defense', y= 'Type 1', data=df) plt.xticks (rotation=-45)

# Make a Bar graph of Defense statistics for Type 1 sns.barplot (x= 'Defense', y= 'Type 1', data=df)

# Make a violin plot of the Defense data for Type 1 sns.violinplot (x= 'Defense', y= 'Type 1', data=df)

# Repeat the plot in the previous cell but change palette to 'prism' and change size sns.violinplot (x= 'Defense', y= 'Type 1', data=df, palette = 'prism')

# Overlaying plots - overlay violin plot of Defense with actual points # To do this (1) increase figure size using ```plt.figure(figsize = (10,6) )```; # (2) create violin plot and set inner = None to get rid of the bars inside violin plot; # (3) rotate x-axis labels for readability; # (4) create swarmplot for points and set ```color='k'``` to create the points in black; # (5) add title "Defense Data for Type 1" # plt.figure(figsize = (10,6) ) sns.violinplot (x= 'Defense', y= 'Type 1', data=df, palette = 'prism', inner = None) sns.swarmplot (x = 'Defense', y= 'Type 1', data=df, color= 'k') plt.title = ('Defense Data for Type 1')

# Import libraries import numpy as np import matplotlib.pyplot as plt import pandas as pd from pandas import DataFrame, Series import seaborn as sns

# Import LinearRegression function from scikit-learn from sklearn.linear_model import LinearRegression

# Read in data from file insurance.csv and create a DataFrame; print out some lines # df = pd.read_csv ('insurance.csv') df.head (4)

# Set background grid for Seaborn plots sns.set_style ('whitegrid')

# Create scatter plot of charges vs BMI with color indiciating whether patient is # smoker or not sns.relplot (x= 'charges', y= 'bmi', data=df, hue= 'smoker')

# Get data to use for linear regression # Right now we see if there is a relationship between insurance charges and bmi charges= df.charges.values n= len(charges) charges= np.reshape (charges,(n,1)) bmi= df.bmi.values bmi= np.reshape (bmi, (n,1))

# Make bmi an n by 1 array and charges n by 1 print ('charges reshaped', charges) print ('bmi reshaped', bmi)

# Create model and fit data lr=LinearRegression()

# write out equation of line lr.fit(bmi,charges) print ('intercept', lr.intercept_) print ('slope', lr.coef_) print ('The equation which fits the data in a linear regression sense is:') print (f'{round (lr.intercept_[0],4)} + {round(lr.coef_[0,0],4)} times bmi')

# Use regplot to plot data and line sns.regplot (x= 'charges', y= 'bmi', data=df)

# predict insurance costs for a person with BMI 31.7; round answer to nearest cent # # Note that this value agrees with plot above because when x=31.7 y is around 14,000 print (f' insurance cost of a person with a bmi of 31.7 is {1192.9372 + 393.873*31.7} ')