Day 25 of 100

Whilst I had heard about the Pandas library, today I learnt how to use it. I also took some time later to just go though the 'getting started' part of the documentation(which can be found here). I took some notes and then did a project in which you have to guess all 50 of the United States. This list of various bits of code is ordered from what I did first and my final project at the bottom.

notes.py

print("------------------------------------------------------")

import csv
# Reading a file and collecting data from one of its
#   columns and converting it to an integer
with open("weather_data.csv") as data_file:
    data = csv.reader(data_file)
    temp = []
    for row in data:
        if row == ['day', 'temp', 'condition']:
            pass
        else:
            degree = int(row[1])
            temp.append(degree)
    print(temp)

print("------------------------------------------------------")

import pandas as pd
# With Pandas
data = pd.read_csv('weather_data.csv')
print(data["temp"])

print("------------------------------------------------------")

# Turns DataFrame to dictionary
data_dict = data.to_dict()
print(data_dict)

# Turns Series to list
temp_list = data["temp"].to_list()
print(temp_list)

print("------------------------------------------------------")

average = sum(temp_list) / len(temp_list)
# OR
average = data["temp"].mean()

print(data["temp"].max())

print("------------------------------------------------------")

# Get data in columns
print(data["condition"])
print(data.condition) #Behind the scenes, pandas
                    # converts each of the columns into attributes
# Get data in rows
print(data[data.day == "Monday"])
print(data[data.temp == data.temp.max()])

monday = data[data.day == "Monday"]
fahrenheit = monday["temp"] * 1.8 + 32
print(fahrenheit)

print("------------------------------------------------------")

# Create DataFrame from scratch
newdata_dict = {"names" : ["John", "Rebecca", "Myles", "Styles", "Anthony"],
                "test scores" : [24, 99, 57, 78, 80]}

data = pd.DataFrame(newdata_dict)
data.to_csv("new_data.csv", index=False)

weather_data.csv

day,temp,condition
Monday,12,Sunny
Tuesday,14,Rain
Wednesday,15,Rain
Thursday,14,Cloudy
Friday,21,Sunny
Saturday,22,Sunny
Sunday,24,Sunny

new_data.csv (created once notes.py runs)

names,test scores
John,24
Rebecca,99
Myles,57
Styles,78
Anthony,80

Squirrels!

The squirrel data for this project can be found here.

import pandas as pd
# TODO : take the Primary Fur Color column and make a
#  new .csv file that contains the three colours and
#  how many squirrels are in each one

black = 0
gray = 0
cinnamon = 0

data = pd.read_csv("squirrel_data.csv")
for color in data["Primary Fur Color"] :
    if color == "Black" :
        black += 1
    elif color == "Gray" :
        gray += 1
    else:
        cinnamon += 1

small_squirrel_data = {"Colour" : ["Black", "Gray", "Cinnamon"],
                       "Count" : [black, gray, cinnamon],}
data = pd.DataFrame(small_squirrel_data)
data.to_csv("small_squirrel_data.csv", index=False)

Output CSV file (small_squirrel_data.csv)

Colour,Count
Black,103
Gray,2473
Cinnamon,447

Main Project - Guess the USA's States

main.py

import pandas as pd
import turtle
import time

screen = turtle.Screen()
screen.title("U.S.A State Game")
image = "blank_states_img.gif"
screen.addshape(image)
screen.setup(height=500,width=730)
screen.bgpic("blank_states_img.gif")
turtle.shape(image)

# TODO : Get x and y values for all states on the image
# def mouse_click_coord(x,y):
#     print(x,y)
#
# turtle.onscreenclick(mouse_click_coord)
# turtle.mainloop()

game_on = True
states_guessed = 0
correct_guess = ""
guessed_states = []
pen = turtle.Turtle()
pen.penup()
pen.hideturtle()
pen.speed(0)

while game_on:
    answer_state = screen.textinput(title="Guess a state",
                                    prompt=f"{states_guessed}/50 states guessed", )

    states_list = pd.read_csv("50_states.csv")

    for states in states_list.state:
        if states == answer_state.title():
            correct_guess = answer_state.title()

            if correct_guess not in guessed_states:
                states_guessed += 1
                guessed_states.append(correct_guess)
                row_list = states_list[states_list.state == correct_guess]
                row_list = row_list.to_dict()
                xcor = list(row_list['x'].values())[0]
                ycor = list(row_list['y'].values())[0]
                pen.goto(x = xcor, y = ycor)
                pen.write(correct_guess, align="right", font=("Courier", 7, "bold"))

    if states_guessed == 50:
        screen.textinput("Finished", "You have guessed all the states!")
        time.sleep(1)
        game_on = False

screen.exitonclick()

50_states.csv
Note - the coordinates may not be exact for everyone, their a bit off for me as well but I can't be asked to individually change them all.

state,x,y
Alabama,139,-77
Alaska,-204,-170
Arizona,-203,-40
Arkansas,57,-53
California,-297,13
Colorado,-112,20
Connecticut,297,96
Delaware,275,42
Florida,220,-145
Georgia,182,-75
Hawaii,-317,-143
Idaho,-216,122
Illinois,95,37
Indiana,133,39
Iowa,38,65
Kansas,-17,5
Kentucky,149,1
Louisiana,59,-114
Maine,319,164
Maryland,288,27
Massachusetts,312,112
Michigan,148,101
Minnesota,23,135
Mississippi,94,-78
Missouri,49,6
Montana,-141,150
Nebraska,-61,66
Nevada,-257,56
New Hampshire,302,127
New Jersey,282,65
New Mexico,-128,-43
New York,236,104
North Carolina,239,-22
North Dakota,-44,158
Ohio,176,52
Oklahoma,-8,-41
Oregon,-278,138
Pennsylvania,238,72
Rhode Island,318,94
South Carolina,218,-51
South Dakota,-44,109
Tennessee,131,-34
Texas,-38,-106
Utah,-189,34
Vermont,282,154
Virginia,234,12
Washington,-257,193
West Virginia,200,20
Wisconsin,83,113
Wyoming,-134,90