File size: 3,103 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 | """
Ashley Wu
Processes data for app
"""
import pandas as pd
import numpy as np
import gradio as gr
import datetime
import utils
#TODO: Add data preview and also do some output shenanigans, but that can wait for a little bit
def process_csv(file):
"""
Create and clean dataframe
Args:
file: The uploaded file object from Gradio
Returns:
A pandas DataFrame to display in Gradio
"""
if file is None:
return "No file uploaded"
try:
# Read the CSV file
df = pd.read_csv(file.name)
# Detect Null values
null_data = df.isnull().sum()
if df.isnull().values.any():
gr.Warning("Null data detected! Removing rows with null values", duration=5)
df = df.dropna()
df_basics = f"The shape of this dataframe is {str(df.shape)} \n {df.describe()} \n Null data: \n {null_data}"
# Return the dataframe for display
return df, df_basics
except Exception as e:
raise gr.Error(f"Error reading CSV: {str(e)}", duration=10)
def save_csv(dataframe):
"""
Save the modified dataframe to a CSV file.
Args:
dataframe: The modified pandas DataFrame
Returns:
Path to the saved CSV file
"""
if dataframe is None:
return None
output_path = "modified_data.csv"
dataframe.to_csv(output_path, index=False)
return output_path
def set_max(max_value, df, column):
"""
Docstring for update_max
:param df: Description
:param max_value: Description
"""
filtered_df = df[df[column] < max_value]
return filtered_df
def set_min(min_value, df, column):
"""
Docstring for update_max
:param df: Description
:param max_value: Description
"""
filtered_df = df[df[column] > min_value]
return filtered_df
def set_categories(removals, df, column):
"""
Removes the selected element's row from the dataframe
Args:
removals: list of elements to be removed
df: dataframe
column: selected column to find values of
"""
df = utils.detect_categories(df)
for row in removals:
df = df[df[column] != row]
return df
def submit_dates(df, max_date, min_date, column):
"""
Filters all dates larger than the max_date and lower than the min_date
Args:
max_date: maximum date
df: dataframe
column: column of dataframe to filter
Returns:
filtered_df: filtered dataframe
"""
df = utils.detect_dates(df)
filtered_df = df
try:
if max_date is not None:
filtered_df = filtered_df[filtered_df[column] <= max_date]
if min_date is not None:
filtered_df = filtered_df[filtered_df[column] >= min_date]
except:
raise gr.Error("The max date is not in the correct format", duration=1)
return filtered_df
|