# 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
for i in range(0, 100):
print(i)
0
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
# print out the data types of all features using .dtypes (no parentheses)
# print out the column names using .columns
# Create a pandas Series for the feature Speed; print out type
# Create a NumPy array for the feature Speed (use.values) ; print out type
# Make 1D NumPy arrays from the features Attack and Defense and do a scatter plot
# using matplotlib
#
# Create a new DataFrame "df_mod" which is same as original but we drop "Type 2" feature; print out to check
# 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
# print out the data types of all features using .dtypes (no parentheses)
# print out the column names using .columns
# Create a pandas Series for the feature Speed; print out type
# Create a NumPy array for the feature Speed (use.values) ; print out type
# Make 1D NumPy arrays from the features Attack and Defense and do a scatter plot
# using matplotlib
#
# Create a new DataFrame "df_mod" which is same as original but we drop "Type 2" feature; print out to check
# 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
#
# Set background grid for Seaborn plots
# Create scatter plot of charges vs BMI with color indiciating whether patient is
# smoker or not
# Get data to use for linear regression
# Right now we see if there is a relationship between insurance charges and bmi
# Make bmi an n by 1 array and charges n by 1
# Create model and fit data
# write out equation of line
# Use regplot to plot data and line
# 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