Codecademy export

script.py

import codecademylib3_seaborn
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np

# load rankings data here:
wood = pd.read_csv("Golden_Ticket_Award_Winners_Wood.csv")
steel = pd.read_csv('Golden_Ticket_Award_Winners_Steel.csv')

wood.rename(columns = {
  "Supplier" : "supplier",
  "Rank" : "rank_s",
  "Name" : "name",
  "Park" : "park",
  "Location" : "location",
  "Year Built" : "year_built",
  "Points" : "points",
  "Year of Rank" : "year_of_rank"
}, inplace = True)

steel.rename(columns = {
  "Supplier" : "supplier",
  "Rank" : "rank_s",
  "Name" : "name",
  "Park" : "park",
  "Location" : "location",
  "Year Built" : "year_built",
  "Points" : "points",
  "Year of Rank" : "year_of_rank"
}, inplace = True)

print (wood.supplier.nunique())
print (steel.supplier.nunique())

print (wood.head())
print (steel.head())

# write function to plot rankings over time for 1 roller coaster here:
def coaster_rankings(coaster_name, park_name, material):
  if material == 'wood':
    select_all_coaster_datas = wood[(wood.name == coaster_name) & (wood.park == park_name)]
    
  if material == "steel":
    select_all_coaster_datas = steel[(steel.name == coaster_name) & (steel.park == park_name)]
    
  #if (material != "wood") & (material !="steel"):
    #print("error in materials/Can't find rollar coaster")
    
  x_values = select_all_coaster_datas.year_of_rank
  y_values = select_all_coaster_datas.rank_s
  outcome = plt.figure(figsize = (10,8))
  plt.plot(range(len(x_values)), y_values, marker = "o", linewidth = 2, color = "green")
  ax = plt.subplot()
  ax.set_xticks(range(len(x_values)))
  ax.set_xticklabels(x_values)
  ax.invert_yaxis()
  plt.xlabel("Year of Ranking")
  plt.ylabel("Ranking")
  plt.title("Ranking for " + coaster_name + " Over Time")
  plt.show()

  
coaster_rankings("El Toro", "Six Flags Great Adventure", "wood")




plt.clf()

# write function to plot rankings over time for 2 roller coasters here:

def coaster_rankings(coaster_name1, park_name1, material1, coaster_name2, park_name2, material2):
  if material1 == 'wood':
    select_all_coaster_datas1 = wood[(wood.name == coaster_name1) & (wood.park == park_name1)]
  if material2 == "wood":
    select_all_coaster_datas2 = wood[(wood.name == coaster_name2) & (wood.park == park_name2)]
    
  if material1 == "steel":
    select_all_coaster_datas1 = steel[(steel.name == coaster_name1) & (steel.park == park_name1)]
  if material2 == "steel":
    select_all_coaster_datas2 = steel[(steel.name == coaster_name2) & (steel.park == park_name2)]
    
  #Now plot the first line.   
  x_values1 = select_all_coaster_datas1.year_of_rank
  y_values1 = select_all_coaster_datas1.rank_s
  plt.figure(figsize = (10,8))
  plt.plot(range(len(x_values1)), y_values1, marker = "o", linewidth = 2, label = coaster_name1)
  ax = plt.subplot()
  ax.set_xticks(range(len(x_values1)))
  ax.set_xticklabels(x_values1)
  ax.invert_yaxis()
  plt.xlabel("Year of Ranking")
  plt.ylabel("Ranking")
  plt.title("Ranking for Two Roller Coaster Over Time")
  
  
  #Now plot the second line.
  x_values2 = select_all_coaster_datas2.year_of_rank
  y_values2 = select_all_coaster_datas2.rank_s
  plt.plot(range(len(x_values2)), y_values2, marker = "o", linewidth = 2, label = coaster_name2)
  
  plt.legend()
  plt.show()

  
coaster_rankings("El Toro", "Six Flags Great Adventure", "wood", "Boulder Dash", "Lake Compounce", "wood")




plt.clf()

# write function to plot top n rankings over time here:
def plot_top_n(material, n):
  #Select all the datas that are top n.
  top_n_rankings = material[material.rank_s <= n]
  #Select one specific roller coaster's datas.
  for one_roller_coaster_name in set(top_n_rankings.name):
      one_roller_coaster_datas = top_n_rankings[top_n_rankings.name == one_roller_coaster_name]
      plt.plot(one_roller_coaster_datas.year_of_rank, one_roller_coaster_datas.rank_s, marker = "o", label = one_roller_coaster_name)
  plt.legend()
  plt.title("Top " + str(n) + " Roller Coasters' Rankings")
  plt.xlabel("Year of Rank")
  plt.ylabel("Rankings")
  ax = plt.subplot()
  ax.invert_yaxis()
  plt.show()


plot_top_n(wood, 5)






plt.clf()

# load roller coaster data here:

roller_coasters = pd.read_csv("roller_coasters.csv")
print (roller_coasters.head())

# write function to plot histogram of column values here:

def plot_a_hist(dataframe, the_column):
  datas_from_the_column_to_plot = dataframe[the_column]
  plt.hist(datas_from_the_column_to_plot.dropna(), normed = True)
  plt.title("The Distribution of " + the_column + " for Roller Coasters")
  plt.xlabel(the_column)
  plt.ylabel("Frequency")
  plt.show()

plot_a_hist(roller_coasters, "speed")
plot_a_hist(roller_coasters, "height")
plot_a_hist(roller_coasters, "length")
plot_a_hist(roller_coasters, "num_inversions")


#plot the histogram for height
def plot_hist_for_height(dataframe):
  datas_of_height = dataframe.height
  percentile_90th = np.percentile(datas_of_height, 90)
  percentile_10th = np.percentile(datas_of_height, 10)
  modified_datas_of_height = datas_of_height[(datas_of_height <= percentile_90th) & (datas_of_height >= percentile_10th)] 
  plt.hist(modified_datas_of_height, normed = True)
  plt.axis([10, (percentile_90th+50), 0, 0.6])
  plt.title("The Distribution of Height for Roller Coasters")
  plt.xlabel("Height")
  plt.ylabel("Frequency")
  plt.show()

plot_hist_for_height(roller_coasters)

plt.clf()

# write function to plot inversions by coaster at a park here:

def plot_num_inversions_at_an_amusement_park(dataframe, park_name):
  datas_of_a_park = dataframe[dataframe.park == park_name]
  datas_of_num_inversions = datas_of_a_park.num_inversions
  roller_coaster_name = datas_of_a_park.name
  plt.bar(range(len(roller_coaster_name)), datas_of_num_inversions)
                 
  plt.title("Number of Inversions for each Roller Coaster")
  plt.xlabel("Roller Coaster Name")
  plt.ylabel("Number of Inversions")
  ax = plt.subplot()
  ax.set_xticks(range(len(roller_coaster_name)))
  ax.set_xticklabels(roller_coaster_name, rotation = 90)
  plt.show()

plot_num_inversions_at_an_amusement_park(roller_coasters, "Parc Asterix")








plt.clf()
    
# write function to plot pie chart of operating status here:

def operating_vs_close(dataframe):
  operating = dataframe[dataframe.status == "status.operating"]
  closed = dataframe[dataframe.status == "status.closed.definitely"]
  
  number_of_operating = len(operating)
  number_of_closed = len(closed)
  plt.pie([number_of_operating, number_of_closed], autopct = "%1d%%")
  plt.axis("equal")
  plt.title("Current Running Condition for Roller Coasters")
  plt.legend(["Operating", "Closed Definitely"])
  plt.show()


operating_vs_close(roller_coasters)  


plt.clf()
  
# write function to create scatter plot of any two numeric columns here:

def scatter_plot_for_two_colums(dataframe, column1, column2):
  data_column1 = dataframe[column1]
  data_column2 = dataframe[column2]
  plt.scatter(data_column1, data_column2)
  plt.title("Relationship between " + column1 + " and " + column2)
  plt.xlabel(column1)
  plt.ylabel(column2)
  plt.show()



scatter_plot_for_two_colums(roller_coasters, "length", "speed")


plt.clf()