File size: 3,264 Bytes
6f6318e | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 | """
Ashley Wu 12/4/25
Creates visualizations for frontend of app
"""
import matplotlib.pyplot as plt
import numpy as np
import gradio as gr
import math
import utils
def time_series(df, xcol, ycol):
"""
Creates a time series graph
Args:
df: dataframe
xcol: column of x calues
ycoL: column of y values
Returns:
fig: time series graph
"""
fig, ax = plt.subplots()
if df[ycol].dtype.name == 'object':
raise gr.Error("The Y value can not be a string or a category!", duration=10)
x = df[xcol].to_numpy()
y = df[ycol].to_numpy()
ax.plot(x, y, color='red', linewidth=2, marker='o')
ax.set_xlabel(xcol)
ax.set_ylabel(ycol)
ax.set_title(f"Time Series of {xcol} and {ycol}")
return fig
def bar_chart(df, xcol, ycol, aggmethod):
"""
Creates bar chart of information
Args:
df: dataframe
xcol: column of x values
ycol: column of y values
aggmethod: aggregation method
Return:
fig: bar chart
"""
df = utils.detect_categories(df)
fig, ax = plt.subplots()
if df[ycol].dtype.name == 'category' or df[ycol].dtype.name == 'object':
raise gr.Error("The Y variable can not be a string or a category!", duration=10)
if df[xcol].dtype.name != 'category':
raise gr.Error("The X variable must be a category!")
if aggmethod == 'sum':
y = df.groupby(xcol)[ycol].sum()
elif aggmethod == 'mean':
y = df.groupby(xcol)[ycol].mean()
elif aggmethod == 'count':
y = df[xcol].value_counts().tolist()
elif aggmethod == 'median':
y = df.groupby(xcol)[ycol].median()
else:
y = df[xcol].tolist()
x = df[xcol].unique().tolist()
ax.bar(x, y)
ax.set_xlabel('Category')
ax.set_ylabel(ycol)
ax.set_title(f'{aggmethod} by Category')
ax.set_xticks(ticks=x)
return fig
def histogram(df, col, bins):
"""
Creates a histogram
Args:
df: dataframe
col: data for histogram
bins: number of bins to put histogram data into
Returns:
fig: histogram created
"""
fig, ax = plt.subplots()
bins = math.floor(bins)
if df[col].dtype.name == 'object':
raise gr.Error("The Y value can not be a string or a category!", duration=10)
ax.hist(df[col], bins)
ax.set_xlabel(f'{col}')
ax.set_title(f'Histogram of {col}')
return fig
def scatter(df, xcol, ycol):
"""
Creates a scatter plot
Args:
df: dataframe
xcol: column of x values
ycol: column of y values
Returns:
fig: scatter plot
"""
fig, ax = plt.subplots()
if df[ycol].dtype.name == 'object' or df[xcol].dtype.name == 'object':
raise gr.Error("The X or Y values can not be a string or a category!", duration=10)
x = df[xcol].to_numpy()
y = df[ycol].to_numpy()
ax.plot(x, y, color='red', marker='o')
ax.set_xlabel(xcol)
ax.set_ylabel(ycol)
ax.set_title(f"Scatter Plot of {xcol} and {ycol}")
return fig
|