# Create a dataframe using a NumPy array that is 50 by 4
arr_1 = np.random.randn(50, 4)
df_1 = pd.DataFrame(arr_1, columns=['A','B','C','D'])
df_1.head()

# Compare old plots to a Plotly interactive plot
# You can save as PNG, Zoom, Pan, Turn off & on Data and more

fig = px.line(df_1, title = "Plotly")
fig.show()

df_1.plot()

medals = px.data.medals_long(indexed=False)

fig = px.bar(medals, x='nation', y='count', color='medal', 
             title='Medal Count for Olympic Short Track Speed Skating')
fig.show()

medals = px.data.medals_long(indexed=False)

# Calculate the total medal count for each nation
total_medals = medals.groupby('nation')['count'].sum()

# Calculate the percentage of each medal for each nation
medals['percentage'] = medals['count'] / total_medals[medals['nation']].values * 100

# Create a new column with the medal count and percentage as a string
medals['text'] = medals['count'].astype(str) + ' (' + medals['percentage'].round(1).astype(str) + '%)'

fig = px.bar(medals, 
             x='nation', y='count', 
             color='medal', 
             title='Medal Count for Olympic Short Track Speed Skating',
             custom_data=['percentage'],
             text='text')

fig.show()

df = px.data.gapminder()
print(df.columns)
print(df.head)

gapminder = px.data.gapminder()

# Filter the dataset to include only data from the year 2007
gapminder_2007 = gapminder[gapminder['year'] == 2007]

# Group the data by continent and calculate the sum of the population for each continent
grouped_data = gapminder_2007.groupby('continent', as_index=False)['pop'].sum()

# Rename the columns to match the names expected by px.pie
# grouped_data = grouped_data.rename(columns={'continent': 'names', 'pop': 'values'})

# Assign the result to df
df = grouped_data
df.head()

fig = px.pie(df, values='pop', names='continent', title='World Population by Continent (2007)')
# fig.update_traces(textinfo = "label+percent")
fig.show()

from plotly.subplots import make_subplots

fig = make_subplots(rows=2, cols=2, 
                    subplot_titles=("Linear", "Square", "Cube", "Quarted"))

x = np.arange(-30, 30)

fig.add_trace(go.Scatter(x=x, y=x**1, mode='markers'),
              row=1, col=1)

fig.add_trace(go.Scatter(x=x, y=x**2, mode='markers'),
              row=1, col=2)

fig.add_trace(go.Scatter(x=x, y=x**3, mode='markers'),
              row=2, col=1)

fig.add_trace(go.Scatter(x=x, y=x**4, mode='markers'),
              row=2, col=2)

fig.update_layout(showlegend=False, title="What Nice Graphs!")


fig.show()

import plotly.express as px

# Load the Gapminder dataset
gapminder = px.data.gapminder()

# Group the data by year and calculate the sum of the population for each year
grouped_data = gapminder.groupby('year', as_index=False)['pop'].sum()

# Create a line chart showing global population over time
fig = px.line(grouped_data, x='year', y='pop', title='Global Population Over Time')
fig.show()

import plotly.express as px

# Load the Gapminder dataset
gapminder = px.data.gapminder()
# print(gapminder.columns)

# Create a scatter plot showing life expectancy vs. time
fig = px.scatter(gapminder, x='year', y='lifeExp', trendline='lowess', title='Life Expectancy Over Time')
fig.show()

import plotly.express as px

# Load the Gapminder dataset
gapminder = px.data.gapminder()

# Create a scatter plot showing life expectancy vs. GDP per capita
fig = px.scatter(gapminder, x='gdpPercap', y='lifeExp', color='continent', title='Life Expectancy vs. GDP Per Capita')
fig.show()

import plotly.express as px

# Load the Gapminder dataset
gapminder = px.data.gapminder()

# Create a box plot showing GDP per capita by continent
fig = px.box(gapminder, x='continent', y='gdpPercap', title='GDP Per Capita by Continent')
fig.show()

df = px.data.gapminder()
df_2007 = df.query("year==2007")

# ["plotly", "plotly_white", "plotly_dark", "ggplot2", "seaborn", "simple_white", "none"]

for template in ["plotly", "plotly_dark"]:
    fig = px.scatter(df_2007,
                     x="gdpPercap", y="lifeExp", size="pop", color="continent",
                    #  text = "country",
                    #  labels={'gdpPercap':'GDP per Capita','lifeExp':'Life Expectancy','pop':'Total Population'},
                     log_x=True, size_max=60,
                     template=template, title="Gapminder 2007: '%s' theme" % template)
    fig.show()

z_data = pd.read_csv("https://raw.githubusercontent.com/plotly/datasets/master/api_docs/mt_bruno_elevation.csv")

print(z_data.head())

fig = go.Figure(
    data=go.Surface(z=z_data.values),
    layout=go.Layout(
        title="Mt Bruno Elevation"
        # width=500,
        # height=500,
    ))

fig.update_layout(title="Mt Bruno Elevation:")
fig.show()

import plotly.express as px

df = px.data.iris()

fig = px.scatter(df, x="sepal_length", y="sepal_width", color="species")
fig.show()

import plotly.graph_objs as go
import pandas as pd

stocks_df = px.data.stocks()
print(stocks_df.columns)

# Define the company to display
company = 'AAPL'
# Load the stock price data and filter for the selected company
stocks_df = stocks_df[["date", company]]
stocks_df.columns = ["Date", "Price"]

# dropna() is a method in pandas library that is used to remove any rows with missing or null values in a pandas DataFrame.
# stocks_df = stocks_df.dropna()

# Convert the Date column to a datetime object
stocks_df["Date"] = pd.to_datetime(stocks_df["Date"])

# Define the line chart trace
line_trace = go.Scatter(x=stocks_df["Date"],
                        y=stocks_df["Price"],
                        mode="lines",
                        name=f"{company} Stock Price",
                        line=dict(color="blue", width=2))

# Create the plot with the line chart trace
fig = go.Figure(data=[line_trace])

# Set the chart layout
fig.update_layout(title=f"{company} Stock Price",
                  xaxis_title="Date",
                  yaxis_title="Price")

# Show the chart
fig.show()

import plotly.graph_objs as go
import pandas as pd

# Define the company to display
company = 'AAPL'
stocks_df = px.data.stocks()
print(stocks_df.columns)
# Load the stock price data and filter for the selected company
stocks_df = stocks_df[["date", company]]

# Rename
stocks_df.columns = ["Date", "Price"]
stocks_df = stocks_df.dropna()

# Convert the Date column to a datetime object
stocks_df["Date"] = pd.to_datetime(stocks_df["Date"])

# Add a new column for whether the stock price went up or down that day
stocks_df["Change"] = (stocks_df["Price"] - stocks_df["Price"].shift(1)) > 0
stocks_df.loc[stocks_df.index[0], "Change"] = False

# Define the candlestick chart trace
candlestick_trace = go.Candlestick(x=stocks_df["Date"],
                                   open=stocks_df["Price"],
                                   high=stocks_df["Price"],
                                   low=stocks_df["Price"],
                                   close=stocks_df["Price"],
                                   increasing=dict(line=dict(color="Green")), #00CC94
                                   decreasing=dict(line=dict(color="Red"))) #F50000

# Define the horizontal line trace for the average stock price
avg_price = stocks_df["Price"].mean()
line_trace = go.Scatter(x=[stocks_df["Date"].iloc[0], stocks_df["Date"].iloc[-1]],
                        y=[avg_price, avg_price],
                        name="Average Price",
                        line=dict(color="Grey", dash="dash")) #7F7F7F

# Create the plot with the candlestick chart and the horizontal line
fig = go.Figure(data=[candlestick_trace, line_trace])

# Set the chart layout
fig.update_layout(title=f"{company} Stock Price",
                  yaxis_title="Price",
                  xaxis_rangeslider_visible=False)

# Show the chart
fig.show()