from csv import reader def get_dataset(file_path, with_header=True): opened_file = open(file_path) read_file = reader(opened_file) dataset = list(read_file) if with_header: return dataset[0], dataset[1:] return dataset[1:]

android_header, android_data = get_dataset("googleplaystore.csv") ios_header, ios_data = get_dataset("AppleStore.csv")

def explore_data(dataset, start, end, rows_and_columns=False): dataset_slice = dataset[start:end] for row in dataset_slice: print(row) if rows_and_columns: print("\n") print("Number of rows:", len(dataset)) print("Number of columns:", len(dataset[0]))

del android_data[10472]

def find_duplicate_apps(dataset, index_of_name_column): duplicate_apps = [] unique_apps = [] for app in dataset: name = app[index_of_name_column] if name in unique_apps: duplicate_apps.append(name) else: unique_apps.append(name) return duplicate_apps, unique_apps

def filter_duplicates_by_review(dataset, name_column_index, reviews_column_index): reviews_max = {} for app in dataset: name = app[name_column_index] num_reviews = float(app[reviews_column_index]) if name in reviews_max and reviews_max[name] < num_reviews: reviews_max[name] = num_reviews elif name not in reviews_max: reviews_max[name] = num_reviews unique_data = [] already_added = [] for app in dataset: name = app[name_column_index] num_reviews = float(app[reviews_column_index]) if num_reviews == reviews_max[name] and name not in already_added: unique_data.append(app) already_added.append(name) return unique_data

def is_app_directed_at_english_speakers(app_name): num_non_english_characters = 0 for char in app_name: if ord(char) > 127: num_non_english_characters += 1 if num_non_english_characters > 2: return False return True def filter_non_english_apps(dataset, name_index): filtered_dataset = [] for app in dataset: name = app[name_index] if (is_app_directed_at_english_speakers(name)): filtered_dataset.append(app) return filtered_dataset

def isolate_free_apps(dataset, price_column): free_apps = [] for app in dataset: price = float(app[price_column].replace("$", "")) if price == 0: free_apps.append(app) return free_apps

# functions we'll need for later def freq_table(dataset, index): frequency_table = {} for app in dataset: freq_column = app[index] if freq_column in frequency_table: frequency_table[freq_column] += 1 else: frequency_table[freq_column] = 1 freq_table_as_percentage = {} for key in frequency_table: freq_table_as_percentage[key] = round((frequency_table[key] / len(dataset)) * 100, 2) return freq_table_as_percentage def display_table(dataset, index, limit=10): table = freq_table(dataset, index) table_display = [] for key in table: key_val_as_tuple = (table[key], key) table_display.append(key_val_as_tuple) table_sorted = sorted(table_display, reverse=True) for entry in table_sorted[:limit]: print(entry[1], ":", str(entry[0]) + "%") def display_popularity_by_genre(dataset, genre_index, popularity_index, formatter_cb=None): table = freq_table(dataset, genre_index) popularity_display = [] for genre in table: sum_of_popularity = 0 num_apps_in_genre = 0 for app in dataset: genre_app = app[genre_index] if genre == genre_app: if formatter_cb is not None: metric = formatter_cb(app[popularity_index]) else: metric = float(app[popularity_index]) sum_of_popularity += metric num_apps_in_genre += 1 popularity_display.append((round(sum_of_popularity / num_apps_in_genre), genre, num_apps_in_genre)) for entry in sorted(popularity_display, reverse=True): print(entry[1], ":", entry[0], "|", entry[2], "apps")

def format_installs(installs): installs = installs.replace("+", "") installs = installs.replace(",", "") return float(installs)