import seaborn as sns
import matplotlib.pyplot as plt
import pandas as pd

# Load the "taxis" dataset
taxis = sns.load_dataset('taxis')

# Display basic information about the dataset
print(taxis.info())

# Display summary statistics
print(taxis.describe())

# Check for missing values
print(taxis.isna().sum())

# Replace missing values with zeros
taxis_filled = taxis.fillna(0)

# Verify that there are no more missing values
print(taxis_filled.isna().sum())

# Plot the distribution of fares
plt.figure(figsize=(10, 6))
sns.histplot(taxis_filled['fare'], bins=30, kde=True)
plt.title('Distribution of Taxi Fares')
plt.xlabel('Fare')
plt.ylabel('Frequency')
plt.show()

# Calculate the average fare by passenger count
average_fare_by_passenger = 
taxis.groupby('passengers').fare.mean().reset_index()

# Bar plot of average fare by passenger count
plt.figure(figsize=(6, 4))
plt.bar(average_fare_by_passenger['passengers'], 
average_fare_by_passenger['fare'], color='violet')

plt.title('Average Fare by Passenger Count')
plt.xlabel('Number of Passengers')
plt.ylabel('Average Fare ($)')
plt.xticks(average_fare_by_passenger['passengers'])
plt.grid(False)
plt.show()

diamonds = sns.load_dataset('diamonds')

# Display basic information about the dataset
print(diamonds.info())

# Display summary statistics
print(diamonds.describe())

# Display the first few rows of the dataset
print(diamonds.head())

#Display first and last rows as common result
print(pd.concat([diamonds.head(), diamonds.tail()])

# Count the number of rows in the dataset
num_rows = diamonds.shape[0]
print(f"The number of rows in the diamonds dataset is: {num_rows}")

# List the name of headers
for headers in diamonds.columns:
    print(headers)

# Select data from diamonds dataset: 
#5 selected columns and 1000 rows + headers
diamonds_data = diamonds[['carat', 'cut', 'color',
                          'clarity', 'price']].head(1001)

# Show selected data
print(diamonds_data)

# or as dataset with pandas
df_diamonds_data = pd.DataFrame(data=diamonds_data)
print(df_diamonds_data)

# Count how many Ideal score is in column cut
print(df_diamonds_data['cut'].value_counts()['Ideal'])

# Drop one column in dataset
df_diamonds_data.drop('clarity',
                      axis=1,
                      inplace= True)
print(df_diamonds_data)

# Create pivot table
table = pd.pivot_table(df_diamonds_data,
                       values=['color', 'cut'],
                       index=['carat', 'price'],
                       aggfunc={'carat': "mean",
                                'price': ["min", "max", "mean"]})
print(table)

from sklearn import datasets
import seaborn as sns

# List of datasets
#sklearn
print(dir(datasets))
dt_sklearn = dir(datasets)

for d in dt_sklearn:
    if d.startswith("load"):
        print(d)

#seaborn
print(sns.get_dataset_names())
#or
for elem in sns.get_dataset_names():
    print(elem)

#sklearn and pandas
from sklearn.datasets import load_iris
import pandas as pd

# Load the iris dataset
iris = load_iris()

# Convert to pandas DataFrame
iris_df = pd.DataFrame(data=iris.data, columns=iris.feature_names)
iris_df['species'] = iris.target

print(iris_df.head())
print(iris_df[:20])

# Save the DataFrame to a CSV file
iris_df.to_csv('iris_dataset.csv', index=False)

import requests
import pandas as pd
import numpy as np
from sklearn import preprocessing, svm
from sklearn.model_selection import (cross_validate,
                                     train_test_split)
from sklearn.linear_model import LinearRegression
import math

#open file to read it content, features, parameters
FilePath = r"C:\Users\Agnieszka\Desktop\Animals.csv"
GetFile = open(FilePath)
DataFile = GetFile.read()
#print(DataFile)
GetFile.close()

import chardet

with open(FilePath, 'rb') as fp:
    result = chardet.detect(fp.read())
    print(result)  # Wyświetli wykryte kodowanie


df = pd.read_csv(FilePath, sep=';', na_values='No data', 
                 encoding='ascii')
df = df.fillna('0.00')
#print(df)

#creating sum colun from 3 others
df = df[['Moose', 'Boars','Deer','Dama','Fawn']]
df['DeerFamily'] = df['Deer']+df['Fawn']+df['Dama']
df = df[['Moose','Boars','DeerFamily']]
#print(df)

forecast_col = 'DeerFamily'
forecast_out = int(math.ceil(0.1*len(df)))
df['label'] = df[forecast_col].shift(-forecast_out)
#print(df)
df = df.fillna('0.00')
print(df.head(2))
print(df.tail(3))

#regression
X = np.array(df.drop(['label'], axis=1))
print(X[:3])
y = np.array(df['label'])
X = preprocessing.scale(X)
#y = np.array(df('label'))

X_train, X_test, y_train, y_test = (
    train_test_split(X,y,test_size=0.2))

clf = LinearRegression()
clf.fit(X_train, y_train)
accuracy = clf.score(X_test, y_test)

print(accuracy)
#output: -1.1791136212815982

# seaborn
import seaborn as sns
import pandas as pd

# load the dataset
planets_df = sns.load_dataset('planets')
print(planets_df.columns)
print(planets_df.describe())

# Update data in dataframe
planets_df.fillna(0, inplace=True)

print("\n DataFrame Planets column Mass as example \
    after in-place replacement of NaN with zeros:")
print(planets_df['mass'])

Mass_Column = planets_df['mass']
Mass_Column100 = Mass_Column[:100]
print(Mass_Column100)
Mass_List = Mass_Column100.tolist()
print(Mass_List)

# Save column after changes to csv, first 100 rows
Mass_List.to_csv('planets.csv', index=False)

from sklearn import datasets
import seaborn as sns

exercise_df = sns.load_dataset('exercise')
print(exercise_df.head())
print(exercise_df.tail())
print(exercise_df['kind'].drop_duplicates())
''' output:
0        rest
30    walking
60    running
Name: kind, dtype: category
Categories (3, object): ['rest', 'walking', 'running']'''

column = 'pulse'

# Znajdź maksymalną i minimalną wartość
max_value = exercise_df[column].max()
min_value = exercise_df[column].min()

print(f"Max value in column '{column}' is: {max_value}")
print(f"Min value in column '{column}' is: {min_value}")

print(exercise_df['diet'].value_counts())
sorted_data = exercise_df.sort_values(by='time',
                                      ascending=False)
print(sorted_data)

exercise_df['pulse_category'] = (
    exercise_df['pulse'].apply(lambda x:
                               'High' if x > 100 else 'Low'))
print(exercise_df[['pulse', 'pulse_category']])

aggregated = exercise_df.agg({
    'pulse': ['mean', 'max', 'min'],
    'time': ['nunique']
})
print(aggregated)