Python-Online Job 02

# Load the required libraries
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
import networkx as nx
from sklearn.preprocessing import MinMaxScaler

# Read data
transcriptome_data = pd.read_csv('./data/GSE238099.csv')

transcriptome_data = transcriptome_data.replace(0, np.nan)
transcriptome_data.dropna(thresh=6, inplace=True)  # Drop genes with less than 6 samples
transcriptome_data[['t-Cont1', 't-Cont2', 't-Cont3', 't-Cont4', 't-Cont5', 't-Cont6', 't-KD1', 't-KD2', 't-KD3', 't-KD4', 't-KD5', 't-KD6']] = transcriptome_data[['t-Cont1', 't-Cont2', 't-Cont3', 't-Cont4', 't-Cont5', 't-Cont6','t-KD1', 't-KD2', 't-KD3', 't-KD4', 't-KD5', 't-KD6']].fillna(transcriptome_data[['t-Cont1', 't-Cont2', 't-Cont3', 't-Cont4', 't-Cont5', 't-Cont6', 't-KD1', 't-KD2', 't-KD3', 't-KD4', 't-KD5', 't-KD6']].mean())

# Scale the data
scaler = MinMaxScaler()

# min-max data scaling
transcriptome_data[['t-Cont1', 't-Cont2', 't-Cont3', 't-Cont4', 't-Cont5', 't-Cont6', 't-KD1', 't-KD2', 't-KD3', 't-KD4', 't-KD5', 't-KD6']] = scaler.fit_transform(transcriptome_data[['t-Cont1', 't-Cont2', 't-Cont3', 't-Cont4', 't-Cont5', 't-Cont6', 't-KD1', 't-KD2', 't-KD3', 't-KD4', 't-KD5', 't-KD6']])

# Calculate mean expression values
transcriptome_data['Ctrl_mean'] = transcriptome_data[['t-Cont1', 't-Cont2', 't-Cont3', 't-Cont4', 't-Cont5', 't-Cont6']].mean(axis=1)
transcriptome_data['KD_mean'] = transcriptome_data[['t-KD1', 't-KD2', 't-KD3', 't-KD4', 't-KD5', 't-KD6']].mean(axis=1)

# Calculate fold change and p-values
transcriptome_data['fold_change'] = transcriptome_data['KD_mean'] / transcriptome_data['Ctrl_mean']
p_values = []
transcriptome_data[['t-Cont1', 't-Cont2', 't-Cont3', 't-Cont4', 't-Cont5', 't-Cont6', 't-KD1', 't-KD2', 't-KD3', 't-KD4', 't-KD5', 't-KD6']] = transcriptome_data[['t-Cont1', 't-Cont2', 't-Cont3', 't-Cont4', 't-Cont5', 't-Cont6',  't-KD1', 't-KD2', 't-KD3', 't-KD4', 't-KD5', 't-KD6']].astype(float)

# Define the degrees of freedom
df = 6  # 6 samples in each group
from scipy.stats import t
def calculate_p_value(row):
    ctrl_expr = row[['t-Cont1', 't-Cont2', 't-Cont3', 't-Cont4', 't-Cont5', 't-Cont6']]
    kd_expr = row[['t-KD1', 't-KD2', 't-KD3', 't-KD4', 't-KD5', 't-KD6']]

    # Calculate the mean and standard deviation
    ctrl_mean = ctrl_expr.mean()
    kd_mean = kd_expr.mean()
    ctrl_std = ctrl_expr.std(ddof=1)
    kd_std = kd_expr.std(ddof=1)

    # Calculate the standard error
    stderr = np.sqrt(ctrl_std ** 2 / len(ctrl_expr) + kd_std ** 2 / len(kd_expr))

    # Calculate the t-value
    t_value = (kd_mean - ctrl_mean) / stderr

    # Calculate the p-value
    p_value = 2 * t.cdf(-np.abs(t_value), df)

    return p_value


# Use the function to calculate p-values
transcriptome_data['p_value'] = transcriptome_data.apply(calculate_p_value, axis=1)
transcriptome_data = transcriptome_data[~transcriptome_data['p_value'].isna()]
# Define the fold change threshold
fold_change_threshold = 2

# Select differentially expressed genes
differentially_expressed_genes = transcriptome_data[(transcriptome_data['fold_change'] >= fold_change_threshold) | (transcriptome_data['fold_change'] <= 0.5)]

# Output summary statistics
control_mean = transcriptome_data['Ctrl_mean'].mean()
kd_mean = transcriptome_data['KD_mean'].mean()
differential_genes_count = len(differentially_expressed_genes)

# Importing the libraries
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, confusion_matrix
import seaborn as sns
from matplotlib.font_manager import FontProperties
import matplotlib.pyplot as plt

# Load the titanic_data
titanic_data = pd.read_csv('./data/titanic.csv')
print(titanic_data.head())

# Pre-process the titanic_data

# Drop the columns that are not useful
x = titanic_data.drop(['Survived', 'Name', 'Sex'], axis=1)
y = titanic_data['Survived']

# Split the titanic_data into training and testing sets
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=42)

# Train the model
model = LogisticRegression()
model.fit(x_train, y_train)

# Make predictions
y_pred = model.predict(x_test)

# Plot the confusion matrix
cm = confusion_matrix(y_test, y_pred)
plt.figure(figsize=(16, 12), dpi=200)
sns.heatmap(cm, annot=True, annot_kws={ 'fontproperties': custom_font}, cmap='GnBu')
plt.xlabel('Predicted', fontproperties=custom_font)
plt.ylabel('Actual', fontproperties=custom_font)
plt.xticks(font=custom_font)
plt.yticks(font=custom_font)
plt.title('Confusion Matrix', fontproperties=custom_font)

import wikipedia

def get_wiki_name_from_file(file_name):
    with open(file_name, 'r') as file:
        keywords = [line.strip() for line in file.readlines()]
    return keywords

def fetch_summaries(keywords, output_file, input_file):
    for keyword in keywords:
        print(f"Fetching summary for '{keyword}'")
        try:
            summary = wikipedia.summary(keyword)
            write_summary_to_file(keyword, summary, output_file)
        except wikipedia.exceptions.DisambiguationError as e:
            summary = wikipedia.summary(e.options[0])
            write_summary_to_file(keyword, summary, output_file)
        except wikipedia.exceptions.PageError:
            print(f"Page for '{keyword}' does not exist.")

def write_summary_to_file(keyword, summary, output_file):
    with open(output_file, 'a') as file:
        file.write(f"{keyword}: {summary}\n")

if __name__ == '__main__':
    # Define the input and output file paths
    # default input file path: ./data/wikipedia.txt
    input_file_path = input('Enter the file which contains the keywords: ')
    input_file_path = "./data/wikipedia.txt"
    # default output file path: ./output/output.txt
    output_file_path = input('Enter the file to save the summaries: ')
    output_file_path = "./output/output.txt"

    # Read keywords from file
    keywords = get_wiki_name_from_file(input_file_path)

    # Fetch summaries from Wikipedia
    fetch_summaries(keywords, output_file_path, input_file_path)