1. Time series analysis
import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import matplotlib as mpl
import matplotlib.pyplot as plt # data
visualization
import seaborn as sns #
statistical data visualization
# Input data files are available in the read-only
"../input/" directory
# For example, running this (by clicking run or pressing
Shift+Enter) will list all files under the input directory
import os
for dirname, _, filenames in os.walk('/kaggle/input'):
for filename in filenames:
print(os.path.join(dirname, filename))
path = '/kaggle/input/air-passengers/AirPassengers.csv'
df = pd.read_csv(path)
df.head()
df.columns = ['Date','Number of Passengers']
df.head()
def plot_df(df, x, y, title="", xlabel='Date', ylabel='Number of Passengers', dpi=100):
plt.figure(figsize=(15,4), dpi=dpi)
plt.plot(x, y, color='tab:red')
plt.gca().set(title=title, xlabel=xlabel, ylabel=ylabel)
plt.show()
plot_df(df, x=df['Date'], y=df['Number of Passengers'], title='Number of US Airline passengers from 1949 to 1960')
OUTPUT
2. categorical analysis
# Import libraries
from matplotlib import pyplot as plt
import numpy as np
# Creating dataset
cars = ['AUDI', 'BMW', 'FORD',
'TESLA', 'JAGUAR', 'MERCEDES']
data = [23, 17, 35, 29, 12, 41]
# Creating plot
fig = plt.figure(figsize=(10, 7))
plt.pie(data, labels=cars)
# show plot
plt.show()
OUTPUT
3. Sentiment analysisimport numpy as np
import matplotlib.pyplot as plt
# creating the dataset
data = {'C':20, 'C++':15, 'Java':30,
'Python':35}
courses = list(data.keys())
values = list(data.values())
fig = plt.figure(figsize = (10, 5))
# creating the bar plot
plt.bar(courses, values, color ='maroon',
width = 0.4)
plt.xlabel("Courses offered")
plt.ylabel("No. of students enrolled")
plt.title("Students enrolled in different courses")
plt.show()
OUTPUT
4. Heatmap# importing the modules
import numpy as np
import seaborn as sn
import matplotlib.pyplot as plt
# generating 2-D 10x10 matrix of random numbers
# from 1 to 100
data = np.random.randint(low = 1,
high = 100,
size = (10, 10))
print("The data to be plotted:\n")
print(data)
# plotting the heatmap
hm = sn.heatmap(data = data)
# displaying the plotted heatmap
plt.show()
OUTPUT
5. Visual story telling using scatterplot
# Import necessary libraries
import altair as alt
from vega_datasets import data
iris = data.iris()
# Create a scatter plot
scatter_plot = alt.Chart(iris).mark_point().encode(
x='sepalLength',
y='petalLength',
color='species'
)
scatter_plot
OUTPUT
6. 3D Plot
# importing mplot3d toolkits
from mpl_toolkits import mplot3d
import numpy as np
import matplotlib.pyplot as plt
fig = plt.figure()
# syntax for 3-D projection
ax = plt.axes(projection ='3d')
# defining axes
z = np.linspace(0, 1, 100)
x = z * np.sin(25 * z)
y = z * np.cos(25 * z)
c = x + y
ax.scatter(x, y, z, c = c)
# syntax for plotting
ax.set_title('3d Scatter plot geeks for geeks')
plt.show()
OUTPUT
7. Write a program using matplotlib libraryimport matplotlib.pyplot as plt
import numpy as np
x = np.array([5,7,8,7,2,17,2,9,4,11,12,9,6])
y = np.array([99,86,87,88,111,86,103,87,94,78,77,85,86])
plt.scatter(x, y)
plt.show()
OUTPUT
8. Write a program using seaborn# import the required library
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
% matplotlib inline
# load the dataset
df = pd.read_csv("tips.csv")
# display 5 rows of dataset
df.head()
df.boxplot(by ='day', column =['total_bill'], grid = False)
OUTPUT
9. Write python code using legend()
# importing modules
import numpy as np
import matplotlib.pyplot as plt
# Y-axis values
y1 = [2, 3, 4.5]
# Y-axis values
y2 = [1, 1.5, 5]
# Function to plot
plt.plot(y1)
plt.plot(y2)
# Function add a legend
plt.legend(["blue", "green"], loc="lower right")
# function to show the plot
plt.show()
OUTPUT
10. Scaling
import pandas as pd
from sklearn.preprocessing import StandardScaler
# Read Data from CSV
data = read_csv('Geeksforgeeks.csv')
data.head()
# Initialise the Scaler
scaler = StandardScaler()
# To scale data
scaler.fit(data)
OUTPUT
Speed Meter code in python visualization
import plotly.graph_objects as go
fig = go.Figure(go.Indicator(
mode = "gauge+number+delta",
value = 420,
domain = {'x': [0, 1], 'y': [0, 1]},
title = {'text': "Speed", 'font': {'size': 24}},
delta = {'reference': 400, 'increasing': {'color': "RebeccaPurple"}},
gauge = {
'axis': {'range': [None, 500], 'tickwidth': 1, 'tickcolor': "darkblue"},
'bar': {'color': "darkblue"},
'bgcolor': "white",
'borderwidth': 2,
'bordercolor': "gray",
'steps': [
{'range': [0, 250], 'color': 'cyan'},
{'range': [250, 400], 'color': 'royalblue'}],
'threshold': {
'line': {'color': "red", 'width': 4},
'thickness': 0.75,
'value': 490}}))
fig.update_layout(paper_bgcolor = "lavender", font = {'color': "darkblue", 'family': "Arial"})
fig.show()
3D area plot
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
import numpy as np
# Define the figure and 3D axis
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
# Create data
x = np.linspace(-5, 5, 100)
y = np.linspace(-5, 5, 100)
x, y = np.meshgrid(x, y)
z = np.sin(np.sqrt(x**2 + y**2))
# Plot the surface
surf = ax.plot_surface(x, y, z, cmap='viridis')
# Add a color bar which maps values to colors
fig.colorbar(surf, shrink=0.5, aspect=5)
# Set labels
ax.set_xlabel('X axis')
ax.set_ylabel('Y axis')
ax.set_zlabel('Z axis')
# Show the plot
plt.show()
Circular bar plot with labels
# Import matplotlib
import matplotlib.pyplot as plt
# import pandas for data wrangling
import pandas as pd
# Build a dataset
df = pd.DataFrame(
{
'Name': ['item ' + str(i) for i in list(range(1, 51)) ],
'Value': np.random.randint(low=10, high=100, size=50)
})
# Show 3 first rows
df.head(3)
# initialize the figure
plt.figure(figsize=(20,10))
ax = plt.subplot(111, polar=True)
plt.axis('off')
# Draw bars
bars = ax.bar(
x=angles,
height=heights,
width=width,
bottom=lowerLimit,
linewidth=2,
edgecolor="white",
color="#61a4b2",
)
# little space between the bar and the label
labelPadding = 4
# Add labels
for bar, angle, height, label in zip(bars,angles, heights, df["Name"]):
# Labels are rotated. Rotation must be specified in degrees :(
rotation = np.rad2deg(angle)
# Flip some labels upside down
alignment = ""
if angle >= np.pi/2 and angle < 3*np.pi/2:
alignment = "right"
rotation = rotation + 180
else:
alignment = "left"
# Finally add the labels
ax.text(
x=angle,
y=lowerLimit + bar.get_height() + labelPadding,
s=label,
ha=alignment,
va='center',
rotation=rotation,
rotation_mode="anchor")
Radar chart
import matplotlib as mpl
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from matplotlib.cm import ScalarMappable
from matplotlib.lines import Line2D
from mpl_toolkits.axes_grid1.inset_locator import inset_axes
from textwrap import wrap
path = 'https://raw.githubusercontent.com/holtzy/The-Python-Graph-Gallery/master/static/data/hike_data.csv'
data = pd.read_csv(path)
data.head()
data["region"] = data["location"].str.split("--", n=1, expand=True)[0]
# Make sure there's no leading/trailing whitespace
data["region"] = data["region"].str.strip()
# Make sure to use .astype(Float) so it is numeric.
data["length_num"] = data["length"].str.split(" ", n=1, expand=True)[0].astype(float)
summary_stats = data.groupby(["region"]).agg(
sum_length = ("length_num", "sum"),
mean_gain = ("gain", "mean")
).reset_index()
summary_stats["mean_gain"] = summary_stats["mean_gain"].round(0)
trackNrs = data.groupby("region").size().to_frame('n').reset_index()
summary_all = pd.merge(summary_stats, trackNrs, "left", on = "region")
summary_all.head()
# Bars are sorted by the cumulative track length
df_sorted = summary_all.sort_values("sum_length", ascending=False)
# Values for the x axis
ANGLES = np.linspace(0.05, 2 * np.pi - 0.05, len(df_sorted), endpoint=False)
# Cumulative length
LENGTHS = df_sorted["sum_length"].values
# Mean gain length
MEAN_GAIN = df_sorted["mean_gain"].values
# Region label
REGION = df_sorted["region"].values
# Number of tracks per region
TRACKS_N = df_sorted["n"].values
GREY12 = "#1f1f1f"
# Set default font to Bell MT
plt.rcParams.update({"font.family": "Bell MT"})
# Set default font color to GREY12
plt.rcParams["text.color"] = GREY12
# The minus glyph is not available in Bell MT
# This disables it, and uses a hyphen
plt.rc("axes", unicode_minus=False)
# Colors
COLORS = ["#6C5B7B","#C06C84","#F67280","#F8B195"]
# Colormap
cmap = mpl.colors.LinearSegmentedColormap.from_list("my color", COLORS, N=256)
# Normalizer
norm = mpl.colors.Normalize(vmin=TRACKS_N.min(), vmax=TRACKS_N.max())
# Normalized colors. Each number of tracks is mapped to a color in the
# color scale 'cmap'
COLORS = cmap(norm(TRACKS_N))
# Some layout stuff ----------------------------------------------
# Initialize layout in polar coordinates
fig, ax = plt.subplots(figsize=(9, 12.6), subplot_kw={"projection": "polar"})
# Set background color to white, both axis and figure.
fig.patch.set_facecolor("white")
ax.set_facecolor("white")
ax.set_theta_offset(1.2 * np.pi / 2)
ax.set_ylim(-1500, 3500)
# Add geometries to the plot -------------------------------------
# See the zorder to manipulate which geometries are on top
# Add bars to represent the cumulative track lengths
ax.bar(ANGLES, LENGTHS, color=COLORS, alpha=0.9, width=0.52, zorder=10)
# Add dashed vertical lines. These are just references
ax.vlines(ANGLES, 0, 3000, color=GREY12, ls=(0, (4, 4)), zorder=11)
# Add dots to represent the mean gain
ax.scatter(ANGLES, MEAN_GAIN, s=60, color=GREY12, zorder=11)
# Add labels for the regions -------------------------------------
# Note the 'wrap()' function.
# The '5' means we want at most 5 consecutive letters in a word,
# but the 'break_long_words' means we don't want to break words
# longer than 5 characters.
REGION = ["\n".join(wrap(r, 5, break_long_words=False)) for r in REGION]
REGION
# Set the labels
ax.set_xticks(ANGLES)
ax.set_xticklabels(REGION, size=12);
Interactive plots code
https://www.kaggle.com/code/servietsky/plotly-20-best-interactive-graphs-tutorial
No comments:
Post a Comment