df['Size'] = df['Size'].replace('Varies with device', np.nan) # Convert KBs to MB df['Size'] = df['Size'].apply(lambda x: float(x.replace('k', ''))/1024 if 'k' in str(x) else float(x.replace('M', '')) if 'M' in str(x) else float(x))

# THIS IS FOR PRICE COLUMN df['Price'] = df['Price'].astype(str).replace("$","",regex=False).astype(float)

def convert_installs(value): return int(value.replace("+","").replace(",",""))df['Installs'] = df['Installs'].astype(str).map(convert_installs)#THIS IS FOR INSTALL COLUMNS

# THIS IS FOR SIZE SECTION def Convert_Size(value): if 'M' in value: return float(value.replace("M",""))* 1_000_000 elif 'k' in value: return float(value.replace("k",""))* 1_000 elif value == 'Varies with device': return None else: return float(value)df['Size'] = df['Size'].astype(str).map(Convert_Size)

# Function to convert sizes to MB def convert_to_mb(size): if "k" in size: value = float(size.replace("k", "")) return value / 1024 # Convert KB to MB elif "M" in size: return float(size.replace("M", "")) # Already in MB else: return None # Handle unexpected values# Apply the conversion function to the column df["Size_in_MB"] = df["Size"].apply(convert_to_mb) df.head()

all assignments sir, # Function to convert sizes to MB def convert_to_mb(size): if 'm' in size.lower(): # Check if the value is in MB return float(size.lower().replace('m', '')) elif 'k' in size.lower(): # Check if the value is in KB return float(size.lower().replace('k', '')) / 1024 else: return None # Handle unexpected cases# Apply the conversion function to the Size column df['Size'] = df['Size'].apply(convert_to_mb) df.head()df["Price"] = df["Price"].str.replace("$","").astype(float) df['Installs'] = ( df['Installs'] .str.replace(",", "", regex=True) .str.strip() .astype(int) )

ASSIGNMENT # Function to convert sizes to MB def convert_to_mb(size): if 'm' in size.lower(): # Check if the value is in MB return float(size.lower().replace('m', '')) elif 'k' in size.lower(): # Check if the value is in KB return float(size.lower().replace('k', '')) / 1024 else: return None # Handle unexpected cases# Apply the conversion function to the Size column df['Size'] = df['Size'].apply(convert_to_mb) df.head()

df['Price'] = df['Price'].str.replace('$', '')# Remove non-numeric values from the Price column df['Price'] = pd.to_numeric(df['Price'], errors='coerce')# Replace NaN values with 0 df['Price'] = df['Price'].fillna(0)

df['Installs'] = df['Installs'].str.replace('+', '')# Replace 'Free' values with 0 df['Installs'] = df['Installs'].replace('Free', '0')# Convert the Installs column to integer values df['Installs'] = df['Installs'].str.replace(',', '').astype(int)# Define the bins for the Installs column bins_installs = [0, 1000, 10000, 100000, 1000000]# Define the labels for each bin labels_installs = ['Few', 'Some', 'Many', 'Very Many']# Apply the binning method to the Installs column df['Installs_Binned'] = pd.cut(df['Installs'], bins=bins_installs, labels=labels_installs)

def convert_to_mb(size): if isinstance(size, str): if size.endswith('k'): return str(round(float(size[:-1]) / 1024, 2)) + 'M' elif size.endswith('M'): return size elif isinstance(size, float) or isinstance(size, int): return str(size) + 'M' else: return sizedf['Size'] = df['Size'].apply(convert_to_mb)