Lab_ML(07/04/25)

# %%
import matplotlib.pyplot as plt
import seaborn as sns
import numpy as np

# %%
yield_apples =[0.895, 0.91, 0.919, 0.926, 0.929, 0.931]
plt.plot(yield_apples)

# %%
years = [2010, 2011, 2012, 2013, 2014, 2015]
yield_apples =[0.895, 0.91, 0.919, 0.926, 0.929, 0.931]

# %%
plt.plot(years,yield_apples)
plt.xlabel('years')
plt.ylabel('Yield (Tons per hectere)')

# %%
years = range(2000, 2012)
apples = [0.895, 0.91, 0.919, 0.929, 0.931, 0.934, 0.936, 0.937, 0.9375, 0.9372, 0.939, 0.940]
oranges = [0.962, 0.941, 0.930, 0.923, 0.918, 0.908, 0.907, 0.904, 0.901, 0.898, 0.9, 0.896]


# %%
sns.set_style("whitegrid")
plt.plot(years, apples, label='Apples', marker = 'o')
plt.plot(years, oranges, label='Oranges', marker = 'x')
plt.xlabel('Year')
plt.ylabel('Yield')
plt.title('Yield of Apples and Oranges (2000-2011)')
plt.legend()

plt.show()

# %%
sns.set_style("whitegrid")
plt.figure(figsize=(12,6))
plt.plot(years,oranges,marker = 'o')
plt.title("Yeild of Ornages")

# %%
years = range(2000,2006)
apples = [0.35,0.6,0.9,0.8,0.65,0.8]
oranges = [0.4,0.8,0.9,0.7,0.6,0.8]

# %%
sns.set_style("whitegrid")
plt.bar(years,oranges)
plt.xlabel('Year')
plt.ylabel('Yield')
plt.title("Crop Yield")

# %%
sns.set_style("whitegrid")
plt.bar(years,oranges)
plt.bar(years,apples, bottom=oranges)
plt.xlabel('Year')
plt.ylabel('Yield')
plt.title("Crop Yield")

# %%
tips_df = sns.load_dataset("tips")
tips_df

# %%
sns.barplot(x='day',y='total_bill', data=tips_df)

# %%
sns.barplot(x='day',y='total_bill',hue='sex', data=tips_df)

# %%
sns.barplot(x='total_bill',y='day',hue='sex', data=tips_df)

# %%
flower_df = sns.load_dataset("iris")
flower_df.sepal_width

# %%
plt.title('Distribution of Sepal width')
plt.hist(flower_df.sepal_width)

# %%
plt.hist(flower_df.sepal_width, bins=5)

# %%
setosa_df = flower_df[flower_df.species == 'setosa']
versicolor_df = flower_df[flower_df.species == 'versicolor']
virginica_df = flower_df[flower_df.species == 'virginica']


# %%
plt.hist(setosa_df.sepal_width, alpha=0.4, bins=np.arange(2, 5, 0.25), label='Setosa')
plt.hist(versicolor_df.sepal_width, alpha=0.4, bins=np.arange(2, 5, 0.25), label='Versicolor')

# %%
plt.title('Distribution of Sepal width')
plt.hist([setosa_df.sepal_width, versicolor_df.sepal_width, virginica_df.sepal_width],
         bins=np.arange(2,5,0.25),
         stacked=True)
plt.legend(['Setosa','Versicolor','Virginica'])