# 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
s = df.Speed
print(type(s))
s
# Create a NumPy array for the feature Speed (use.values) ; print out type
ss = df.Speed.values
print(type(ss))
print(ss)
# Make 1D NumPy arrays from the features Attack and Defense and do a scatter plot
# using matplotlib
#
aa = df.Attack.values
dd = df.Defense.values
plt.scatter(aa,dd,color='red')
plt.title("Defense vs Attack");
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(6)
# 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)
plt.title("Defense vs Attack");
# Repeat plot in previous cell but use color to indicate Type 1 (hue = )
sns.relplot(x = 'Attack', y = 'Defense' , data = df , hue = 'Type 1')
plt.title("Defense vs Attack w/ Pokemon Types");
# 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 )
plt.title("Defense vs Type 1");
# 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"
#
# 10,6 gave errors not fitting all the points so changed to 10,8
plt.figure(figsize= (10,8));
sns.violinplot(x = 'Defense' , y = 'Type 1', data= df ,palette='prism',inner= None)
plt.xticks(rotation=-45);
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
# 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.scatterplot(x = 'bmi', y= 'charges', data = df, hue= 'smoker');
plt.title('Charges vs BMI for nonsmokers/smokers');
# Get data to use for linear regression
# Right now we see if there is a relationship between insurance charges and bmi
bb = df.bmi.values
cc = df.charges.values
bb
cc
# Make bmi an n by 1 array and charges n by 1
n = len(bb)
bb = np.reshape(bb,(n,1))
cc = np.reshape(cc,(n,1))
# Create model and fit data
lr = LinearRegression();
lr.fit(bb,cc)
# write out equation of line
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 = 'bmi' , y='charges' , data = df)
# predict insurance costs for a person with BMI 31.7; round answer to nearest cent
# 1192.9372 + 393.873 times BMI
BMI_1 = 31.7
Charges = 1192.9372 + 393.873 * BMI_1
print(f'With a BMI of {BMI_1} the predicted insurance cost is ${round(Charges,2)}')
#
# Note that this value agrees with plot above because when x=31.7 y is around 14,000