What The Plot

import pandas as pd
import numpy as np
from matplotlib import pyplot as plt
import seaborn as sns

movies = pd.read_csv('/home/annie/Python/data/MoviesOnStreamingPlatforms.csv')
movies.head()

movies.info()

movie_ratings_df = movies.copy().drop(columns=['Unnamed: 0', 'ID'])
movie_ratings_df['ratings'] = movie_ratings_df['Rotten Tomatoes'].str.replace('/100', '').fillna('0').astype(int)
movie_ratings_df.head()
# movie_ratings_df[movie_ratings_df['ratings'] == '0']

# movie_ratings_df.info()

disney_df = movie_ratings_df.copy().drop(columns=['Netflix', 'Hulu', 'Prime Video'])
disney_df = disney_df[disney_df['Disney+'] == 1]

disney_df.head()

plt.figure(figsize=(10, 6))
sns.scatterplot(x='Year', 
                y='ratings', 
                color='hotpink',
                data=disney_df)
plt.title('Rotten Tomatoes rating for Disney movies by year')
plt.ylabel('Ratings out of 100')
plt.yticks(ticks=range(0,100,5))
plt.xticks(ticks=range(1920, 2024, 10))

#using regplot to add a regression line

# sns.regplot(x='Year', 
#             y='ratings', 
#             data=disney_df,
#             scatter=False, # Disable scatter points to avoid duplicate points
#             color='skyblue')
# plt.ylabel('Ratings out of 100')
# plt.yticks(ticks=range(0,100,5))
plt.show()

disney_df[disney_df['ratings']<20].sort_values(by='Year', ascending=False)

# Using sns.lmplot
sns.lmplot(x='Year', 
                y='ratings', 
                height=6,
                aspect=1.5,
                data=disney_df,
                scatter_kws={'color': 'turquoise'},
                line_kws={'color': 'hotpink'})  # Change the color of the regression line

plt.title('Rotten Tomatoes rating for Disney movies by year')
plt.ylabel('Ratings out of 100')
plt.yticks(ticks=range(0,105,5))
plt.xticks(ticks=range(1920, 2024, 10))
plt.show()

penguin_lter = pd.read_csv('/home/annie/Python/data/penguins_lter.csv')
penguin_df = penguin_lter.dropna(subset=['Sex']) #drop NaNs from Sex column
penguin_df = penguin_df.drop(columns=['Sample Number', 'Individual ID', 'Stage', 'Clutch Completion', 'Clutch Completion', 'Date Egg', 'Comments'])
penguin_df = penguin_df[penguin_df['Sex'] != '.']
penguin_df.head()

# penguin_df.info()

# penguin_lter['Clutch Completion'].unique()
# penguin_lter['studyName'].unique()
# penguin_lter['Date Egg'].unique()
# penguin_lter['Stage'].unique()

# penguin_clean[penguin_clean['Sex']=='.']
penguin_df.head()

penguin_df.sample(5)

penguin_df['Sex'].unique()

#penguin_df

sns.boxplot(data=penguin_df, x='Species', y='Body Mass (g)', palette='mako', hue='Species')
plt.xticks(rotation=45)  
plt.xticks(ticks=[0, 1, 2], labels=['Adelie', 'Chinstrap', 'Gentoo']) # rename ticker labels
plt.title('Body Mass Distribution by species')
plt.show()

sns.boxenplot(data=penguin_df, x='Sex', y='Body Mass (g)', palette='viridis', hue='Sex')
plt.xticks(rotation=45)  
plt.title('Body Mass Distribution by sex')
plt.show()

# #disney_df
# sns.boxplot(x=disney_df['ratings'])
# plt.show()

# sns.boxenplot(x=disney_df['ratings'])
# plt.show()

sns.violinplot(data=penguin_df, x='Species', y='Culmen Length (mm)', hue='Sex', palette='mako')
plt.xticks(ticks=[0, 1, 2], labels=['Adelie', 'Chinstrap', 'Gentoo']) # rename ticker labels
plt.legend(loc="upper left")
plt.title('Culmen Length Distribution by species and sex')
plt.show()

# sns.stripplot(x=disney_df['ratings'])
# plt.show()

sns.stripplot(x='Culmen Depth (mm)', y='Species', hue='Species', data=penguin_df)
plt.yticks(ticks=[0, 1, 2], labels=['Adelie', 'Chinstrap', 'Gentoo'])
plt.title('Culmen Depth Distribution by species')
plt.show()

# sns.swarmplot(x=disney_df['ratings'])
# plt.show()

sns.swarmplot(x='Flipper Length (mm)',y='Species', hue='Species', data=penguin_df)
plt.yticks(ticks=[0, 1, 2], labels=['Adelie', 'Chinstrap', 'Gentoo'])
plt.title('Flipper Length Distribution by species')
plt.show()

disney_df.head(2)

penguin_df.head(2)
# penguin_df['Island'].unique()

sns.histplot(disney_df, x='Year', 
             kde=True, 
             color='hotpink')
plt.title('Distribution of Disney Movies between 1920-2020')
plt.show()

sns.kdeplot(disney_df, x='Year', color='hotpink')
plt.show()

sns.histplot(data=penguin_df, x='Body Mass (g)')
plt.show()

sns.kdeplot(x=disney_df['ratings']) #'Year'
plt.show()

sns.ecdfplot(x=disney_df['ratings'])
plt.show()

adelie_matrix = penguin_df[penguin_df['Species']=='Adelie Penguin (Pygoscelis adeliae)']
adelie_matrix = adelie_matrix.drop(columns=['Species','studyName', 'Region', 'Island', 'Sex', 'Delta 15 N (o/oo)', 'Delta 13 C (o/oo)'])

adelie_matrix.head()

# sns.heatmap(df)
plt.figure(figsize=(8, 6))
sns.heatmap(adelie_matrix.corr(), cmap='mako_r')
plt.title('Correlation Heatmap of Adelie Penguin Measurements')
plt.show()

penguins = sns.load_dataset('penguins')
penguins.head()

peng = sns.FacetGrid(penguins, col='species', #creates separate columns for each unique value in the Species column
                     row='sex', hue='sex', palette="mako_r", sharex=False)
peng.map(sns.histplot, 'bill_length_mm')
# plt.xticks(ticks=[0, 1, 2], labels=['Adelie', 'Chinstrap', 'Gentoo'])

plt.show()

penguin_df.head(2)

sns.pairplot(x_vars = ['Culmen Length (mm)', 'Culmen Depth (mm)', 'Flipper Length (mm)', 'Body Mass (g)'],
             y_vars = ['Culmen Length (mm)', 'Culmen Depth (mm)', 'Flipper Length (mm)', 'Body Mass (g)'],
             hue = 'Species',
             data = penguin_df)
plt.suptitle('Pairplot of Penguin Measurements by Species', y=1.02)
plt.show()

# sns.PairGrid()
pg = sns.PairGrid(penguin_df,
                 x_vars = ['Culmen Length (mm)', 'Culmen Depth (mm)', 'Flipper Length (mm)', 'Body Mass (g)'],
                 y_vars = ['Culmen Length (mm)', 'Culmen Depth (mm)', 'Flipper Length (mm)', 'Body Mass (g)'],
                 hue='Species',
                 palette='cubehelix')
pg.map(sns.scatterplot)
pg.add_legend()
plt.suptitle('Pair Grid showing Penguin Measurements by Species', y=1.02)

plt.show()

pg2 = sns.PairGrid(penguin_df,
                 x_vars = ['Culmen Length (mm)', 'Culmen Depth (mm)', 'Flipper Length (mm)', 'Body Mass (g)'],
                 y_vars = ['Culmen Length (mm)', 'Culmen Depth (mm)', 'Flipper Length (mm)', 'Body Mass (g)'],
                 hue='Species',
                 palette='cubehelix')
pg2.map_upper(sns.scatterplot)
pg2.map_lower(sns.kdeplot)
pg2.map_diag(sns.histplot)
# pg.add_legend()
# plt.suptitle('Pair Grid showing Penguin Measurements by Species', y=1.02)

plt.show()

iris = sns.load_dataset('iris')

iris.sample(5)

iris.info()

# sns.jointplot()

ir = sns.jointplot(data=iris, x="sepal_length", y="petal_length", 
              hue='species', 
              palette='husl')
plt.show()

# sns.jointplot()

ir = sns.jointplot(data=iris, x="sepal_length", y="petal_length", kind='hex')
plt.show()

# sns.JointGrid()

ir2 = sns.JointGrid(data=iris, x="sepal_width", y="petal_width",
              hue='species', 
              palette='husl')

ir2.plot(sns.scatterplot, sns.histplot)
plt.show()

# sns.JointGrid()

ir2 = sns.JointGrid(data=iris, x="sepal_width", y="petal_width",
              hue='species')
                   # height=8)

ir2.plot_joint(sns.scatterplot, s=100, palette='husl', marker="+")
ir2.plot_marginals(sns.histplot, kde=True, palette='mako')
plt.show()

disney_df.head(2)

plt.figure(figsize=(8,6))
sns.lineplot(x='Year', 
                y='ratings', 
                data=disney_df,
                color='hotpink')
plt.title('Disney ratings over time')
plt.xticks(ticks=range(1920, 2024, 10)) 
plt.show()

penguin_df.head(2)

adelie = penguin_df[penguin_df['Species']=='Adelie Penguin (Pygoscelis adeliae)']
adelie

sns.barplot(data=penguin_df, x='Species', y='Culmen Length (mm)', color='lavender')
plt.xticks(ticks=[0, 1, 2], labels=['Adelie', 'Chinstrap', 'Gentoo'])
plt.title('Culmen Length of Penguins by species')
plt.show()

sns.barplot(data=penguin_df, x='Species', y='Culmen Length (mm)', hue='Sex', palette='mako')
plt.xticks(ticks=[0, 1, 2], labels=['Adelie', 'Chinstrap', 'Gentoo'])
plt.title('Culmen Length of Penguins by sex and species')
plt.show()

titanic = sns.load_dataset('titanic')
titanic.head()

sns.barplot(data=titanic, x='pclass', y='age', palette='viridis', hue='alive')
plt.title('Passenger Age by Class and Survival Status on the Titanic')
plt.show()

# sns.pointplot()

sns.pointplot(data=penguin_df, x='Species', y='Culmen Length (mm)', hue='Sex', palette='viridis')
plt.xticks(ticks=[0, 1, 2], labels=['Adelie', 'Chinstrap', 'Gentoo'])
plt.show()

# sns.countplot()
sns.countplot(data=penguin_df, x='Species', color='turquoise')
plt.xticks(ticks=[0, 1, 2], labels=['Adelie', 'Chinstrap', 'Gentoo'])
plt.show()

penguin_df.Species.value_counts()#.sum()

(152/344)*100

(124/344)*100

(68/344)*100