edsl 0.1.38.dev1__py3-none-any.whl → 0.1.38.dev3__py3-none-any.whl

edsl/conversation/car_buying.py

@@ -1,58 +1,58 @@
-from edsl import Agent, AgentList, QuestionFreeText
-from edsl import Cache
-from edsl.conversation.Conversation import Conversation, ConversationList
-
-a1 = Agent(
-    name="Alice",
-    traits={
-        "motivation": """
-    You are Alice. You want to buy a car. You are talking to Bob, a car salesman.
-    It is very important to you that the steering wheel not whiff out of the window while you are driving.
-    Also, the car can have no space for mother-in-law.
-    You brought your brother-in-law along, Paul, who you have an antagonistic relationship with.
-    """
-    },
-)
-a2 = Agent(
-    name="Bob",
-    traits={
-        "motivation": "You are Bob, a car salesman. You are talking to Alice, who wants to buy a car."
-    },
-)
-a3 = Agent(
-    name="Paul",
-    traits={
-        "motivation": "You are Paul, you are Alice's brother. You think her concerns are foolish and you are critical of her."
-    },
-)
-
-c1 = Conversation(agent_list=AgentList([a1, a3, a2]), max_turns=5, verbose=True)
-c2 = Conversation(agent_list=AgentList([a1, a2]), max_turns=5, verbose=True)
-
-c = Cache.load("car_talk.json.gz")
-# breakpoint()
-combo = ConversationList([c1, c2], cache=c)
-combo.run()
-results = combo.to_results()
-results.select("conversation_index", "index", "agent_name", "dialogue").print(
-    format="rich"
-)
-
-q = QuestionFreeText(
-    question_text="""This was a conversation about buying a car: {{ transcript }}. 
-                    Was a brand or style of car mentioned? If so, what was it?
-                    """,
-    question_name="car_brand",
-)
-
-from edsl import QuestionList
-
-q_actors = QuestionList(
-    question_text="""This was a conversation about buying a car: {{ transcript }}. 
-                    Who were the actors in the conversation?
-                    """,
-    question_name="actors",
-)
-
-transcript_analysis = q.add_question(q_actors).by(combo.summarize()).run()
-transcript_analysis.select("car_brand", "actors").print(format="rich")
+from edsl import Agent, AgentList, QuestionFreeText
+from edsl import Cache
+from edsl.conversation.Conversation import Conversation, ConversationList
+
+a1 = Agent(
+    name="Alice",
+    traits={
+        "motivation": """
+    You are Alice. You want to buy a car. You are talking to Bob, a car salesman.
+    It is very important to you that the steering wheel not whiff out of the window while you are driving.
+    Also, the car can have no space for mother-in-law.
+    You brought your brother-in-law along, Paul, who you have an antagonistic relationship with.
+    """
+    },
+)
+a2 = Agent(
+    name="Bob",
+    traits={
+        "motivation": "You are Bob, a car salesman. You are talking to Alice, who wants to buy a car."
+    },
+)
+a3 = Agent(
+    name="Paul",
+    traits={
+        "motivation": "You are Paul, you are Alice's brother. You think her concerns are foolish and you are critical of her."
+    },
+)
+
+c1 = Conversation(agent_list=AgentList([a1, a3, a2]), max_turns=5, verbose=True)
+c2 = Conversation(agent_list=AgentList([a1, a2]), max_turns=5, verbose=True)
+
+c = Cache.load("car_talk.json.gz")
+# breakpoint()
+combo = ConversationList([c1, c2], cache=c)
+combo.run()
+results = combo.to_results()
+results.select("conversation_index", "index", "agent_name", "dialogue").print(
+    format="rich"
+)
+
+q = QuestionFreeText(
+    question_text="""This was a conversation about buying a car: {{ transcript }}. 
+                    Was a brand or style of car mentioned? If so, what was it?
+                    """,
+    question_name="car_brand",
+)
+
+from edsl import QuestionList
+
+q_actors = QuestionList(
+    question_text="""This was a conversation about buying a car: {{ transcript }}. 
+                    Who were the actors in the conversation?
+                    """,
+    question_name="actors",
+)
+
+transcript_analysis = q.add_question(q_actors).by(combo.summarize()).run()
+transcript_analysis.select("car_brand", "actors").print(format="rich")

edsl/conversation/chips.py

@@ -1,95 +1,95 @@
-from typing import Optional
-
-from edsl import Agent, AgentList, QuestionFreeText
-from edsl import Cache
-from edsl import QuestionList
-from edsl import Model
-
-from edsl.conversation.Conversation import Conversation, ConversationList
-
-m = Model("gemini-1.5-flash")
-
-
-class ChipLover(Agent):
-    def __init__(self, name, chip_values, initial_chips, model: Optional[Model] = None):
-        self.chip_values = chip_values
-        self.initial_chips = initial_chips
-        self.current_chips = initial_chips
-        self.model = model or Model()
-        super().__init__(
-            name=name,
-            traits={
-                "motivation": f"""
-            You are {name}. You are negotiating the trading of colored 'chips' with other players. You want to maximize your score.
-            When you want to accept a deal, say "DEAL!" 
-            Note that different players can have different values for the chips.
-            """,
-                "chip_values": chip_values,
-                "initial_chips": initial_chips,
-            },
-        )
-
-    def trade(self, chips_given_dict, chips_received_dict):
-        for color, amount in chips_given_dict.items():
-            self.current_chips[color] -= amount
-        for color, amount in chips_received_dict.items():
-            self.current_chips[color] += amount
-
-    def get_score(self):
-        return sum(
-            self.chip_values[color] * self.current_chips[color]
-            for color in self.chip_values
-        )
-
-
-a1 = ChipLover(
-    name="Alice",
-    chip_values={"Green": 7, "Blue": 1, "Red": 0},
-    model=Model("gemini-1.5-flash"),
-    initial_chips={"Green": 1, "Blue": 2, "Red": 3},
-)
-a2 = ChipLover(
-    name="Bob",
-    chip_values={"Green": 7, "Blue": 1, "Red": 0},
-    initial_chips={"Green": 1, "Blue": 2, "Red": 3},
-)
-
-c1 = Conversation(agent_list=AgentList([a1, a2]), max_turns=10, verbose=True)
-c2 = Conversation(agent_list=AgentList([a1, a2]), max_turns=10, verbose=True)
-
-with Cache() as c:
-    combo = ConversationList([c1, c2], cache=c)
-    combo.run()
-    results = combo.to_results()
-    results.select("conversation_index", "index", "agent_name", "dialogue").print(
-        format="rich"
-    )
-
-    q = QuestionFreeText(
-        question_text="""This was a conversation/negotiation: {{ transcript }}. 
-                        What trades occurred in the conversation?
-                        """,
-        question_name="trades",
-    )
-
-    q_actors = QuestionList(
-        question_text="""Here is a transcript: {{ transcript }}. 
-                        Who were the actors in the conversation?
-                        """,
-        question_name="actors",
-    )
-
-    from edsl import QuestionList
-
-    q_transfers = QuestionList(
-        question_text="""This was a conversation/negotiation: {{ transcript }}. 
-                        Extract all offers and their outcomes.
-                        Use this format: {'proposing_agent':"Alice": 'receiving_agent': "Bob", 'gives':{"Green": 1, "Blue": 2}, 'receives':{"Green": 2, "Blue": 1}, 'accepted':True}
-                        """,
-        question_name="transfers",
-    )
-
-    transcript_analysis = (
-        q.add_question(q_actors).add_question(q_transfers).by(combo.summarize()).run()
-    )
-    transcript_analysis.select("trades", "actors", "transfers").print(format="rich")
+from typing import Optional
+
+from edsl import Agent, AgentList, QuestionFreeText
+from edsl import Cache
+from edsl import QuestionList
+from edsl import Model
+
+from edsl.conversation.Conversation import Conversation, ConversationList
+
+m = Model("gemini-1.5-flash")
+
+
+class ChipLover(Agent):
+    def __init__(self, name, chip_values, initial_chips, model: Optional[Model] = None):
+        self.chip_values = chip_values
+        self.initial_chips = initial_chips
+        self.current_chips = initial_chips
+        self.model = model or Model()
+        super().__init__(
+            name=name,
+            traits={
+                "motivation": f"""
+            You are {name}. You are negotiating the trading of colored 'chips' with other players. You want to maximize your score.
+            When you want to accept a deal, say "DEAL!" 
+            Note that different players can have different values for the chips.
+            """,
+                "chip_values": chip_values,
+                "initial_chips": initial_chips,
+            },
+        )
+
+    def trade(self, chips_given_dict, chips_received_dict):
+        for color, amount in chips_given_dict.items():
+            self.current_chips[color] -= amount
+        for color, amount in chips_received_dict.items():
+            self.current_chips[color] += amount
+
+    def get_score(self):
+        return sum(
+            self.chip_values[color] * self.current_chips[color]
+            for color in self.chip_values
+        )
+
+
+a1 = ChipLover(
+    name="Alice",
+    chip_values={"Green": 7, "Blue": 1, "Red": 0},
+    model=Model("gemini-1.5-flash"),
+    initial_chips={"Green": 1, "Blue": 2, "Red": 3},
+)
+a2 = ChipLover(
+    name="Bob",
+    chip_values={"Green": 7, "Blue": 1, "Red": 0},
+    initial_chips={"Green": 1, "Blue": 2, "Red": 3},
+)
+
+c1 = Conversation(agent_list=AgentList([a1, a2]), max_turns=10, verbose=True)
+c2 = Conversation(agent_list=AgentList([a1, a2]), max_turns=10, verbose=True)
+
+with Cache() as c:
+    combo = ConversationList([c1, c2], cache=c)
+    combo.run()
+    results = combo.to_results()
+    results.select("conversation_index", "index", "agent_name", "dialogue").print(
+        format="rich"
+    )
+
+    q = QuestionFreeText(
+        question_text="""This was a conversation/negotiation: {{ transcript }}. 
+                        What trades occurred in the conversation?
+                        """,
+        question_name="trades",
+    )
+
+    q_actors = QuestionList(
+        question_text="""Here is a transcript: {{ transcript }}. 
+                        Who were the actors in the conversation?
+                        """,
+        question_name="actors",
+    )
+
+    from edsl import QuestionList
+
+    q_transfers = QuestionList(
+        question_text="""This was a conversation/negotiation: {{ transcript }}. 
+                        Extract all offers and their outcomes.
+                        Use this format: {'proposing_agent':"Alice": 'receiving_agent': "Bob", 'gives':{"Green": 1, "Blue": 2}, 'receives':{"Green": 2, "Blue": 1}, 'accepted':True}
+                        """,
+        question_name="transfers",
+    )
+
+    transcript_analysis = (
+        q.add_question(q_actors).add_question(q_transfers).by(combo.summarize()).run()
+    )
+    transcript_analysis.select("trades", "actors", "transfers").print(format="rich")

edsl/conversation/mug_negotiation.py

@@ -1,81 +1,81 @@
-from edsl import Agent, AgentList
-from edsl.conversation.Conversation import Conversation, ConversationList
-
-
-def bargaining_pairs(alice_valuation, bob_valuation):
-    a1 = Agent(
-        name="Alice",
-        traits={
-            "motivation": f"""
-        You are trying to sell your mug to Bob. You value the mug at ${ alice_valuation }---you would rather have the mug than ${alice_valuation}.
-        But you are willing to sell it for ${alice_valuation} or more if Bob is willing to pay that much.
-        You WILL NOT sell for less than ${alice_valuation}.
-        You want to get as much money as possible for the mug.
-        You are an experienced negotiator are strategic in your approach.
-        """
-        },
-    )
-    a2 = Agent(
-        name="Bob",
-        traits={
-            "motivation": f"""You are Bob. You are trying to buy a mug from Alice. You value the mug at ${bob_valuation}. You would rather have the mug than ${bob_valuation}.
-            But you want to pay as little as possible for the mug.
-            You absolutely WILL NOT pay more than ${bob_valuation}.
-            Carefully consider your valuation before making or accepting an offer.
-            You are an experienced negotiator and are strategic in your approach.
-            """
-        },
-    )
-    return AgentList([a1, a2])
-
-
-valuations = [(10, 15), (10, 100), (10, 9)]
-cl = ConversationList(
-    [
-        Conversation(agent_list=bargaining_pairs(*v), max_turns=10, verbose=True)
-        for v in valuations
-    ]
-)
-cl.run()
-results = cl.to_results()
-
-results.select("conversation_index", "index", "agent_name", "dialogue").print(
-    format="rich"
-)
-
-from edsl import (
-    QuestionFreeText,
-    QuestionMultipleChoice,
-    QuestionYesNo,
-    QuestionNumerical,
-)
-
-q_deal = QuestionYesNo(
-    question_text="""This was a negotiation: {{ transcript }}. 
-                     Was a deal reached?
-                    """,
-    question_name="deal",
-)
-
-q_price = QuestionNumerical(
-    question_text="""This was a negotiation: {{ transcript }}.
-    A deal was reached. What was the price of the deal?
-    """,
-    question_name="price",
-)
-
-q_side_deal = QuestionYesNo(
-    question_text="""This was a negotiation: {{ transcript }}.
-    Was there a side deal? I.e., seller agreed to other terms in exchange for a higher price?
-    """,
-    question_name="side_deal",
-)
-
-survey = (
-    q_deal.add_question(q_price)
-    .add_question(q_side_deal)
-    .add_stop_rule("deal", "deal == 'No'")
-)
-
-transcript_analysis = survey.by(cl.summarize()).run()
-transcript_analysis.select("deal", "price", "side_deal").print(format="rich")
+from edsl import Agent, AgentList
+from edsl.conversation.Conversation import Conversation, ConversationList
+
+
+def bargaining_pairs(alice_valuation, bob_valuation):
+    a1 = Agent(
+        name="Alice",
+        traits={
+            "motivation": f"""
+        You are trying to sell your mug to Bob. You value the mug at ${ alice_valuation }---you would rather have the mug than ${alice_valuation}.
+        But you are willing to sell it for ${alice_valuation} or more if Bob is willing to pay that much.
+        You WILL NOT sell for less than ${alice_valuation}.
+        You want to get as much money as possible for the mug.
+        You are an experienced negotiator are strategic in your approach.
+        """
+        },
+    )
+    a2 = Agent(
+        name="Bob",
+        traits={
+            "motivation": f"""You are Bob. You are trying to buy a mug from Alice. You value the mug at ${bob_valuation}. You would rather have the mug than ${bob_valuation}.
+            But you want to pay as little as possible for the mug.
+            You absolutely WILL NOT pay more than ${bob_valuation}.
+            Carefully consider your valuation before making or accepting an offer.
+            You are an experienced negotiator and are strategic in your approach.
+            """
+        },
+    )
+    return AgentList([a1, a2])
+
+
+valuations = [(10, 15), (10, 100), (10, 9)]
+cl = ConversationList(
+    [
+        Conversation(agent_list=bargaining_pairs(*v), max_turns=10, verbose=True)
+        for v in valuations
+    ]
+)
+cl.run()
+results = cl.to_results()
+
+results.select("conversation_index", "index", "agent_name", "dialogue").print(
+    format="rich"
+)
+
+from edsl import (
+    QuestionFreeText,
+    QuestionMultipleChoice,
+    QuestionYesNo,
+    QuestionNumerical,
+)
+
+q_deal = QuestionYesNo(
+    question_text="""This was a negotiation: {{ transcript }}. 
+                     Was a deal reached?
+                    """,
+    question_name="deal",
+)
+
+q_price = QuestionNumerical(
+    question_text="""This was a negotiation: {{ transcript }}.
+    A deal was reached. What was the price of the deal?
+    """,
+    question_name="price",
+)
+
+q_side_deal = QuestionYesNo(
+    question_text="""This was a negotiation: {{ transcript }}.
+    Was there a side deal? I.e., seller agreed to other terms in exchange for a higher price?
+    """,
+    question_name="side_deal",
+)
+
+survey = (
+    q_deal.add_question(q_price)
+    .add_question(q_side_deal)
+    .add_stop_rule("deal", "deal == 'No'")
+)
+
+transcript_analysis = survey.by(cl.summarize()).run()
+transcript_analysis.select("deal", "price", "side_deal").print(format="rich")

edsl/conversation/next_speaker_utilities.py

@@ -1,93 +1,93 @@
-import random
-
-
-def default_turn_taking_generator(agent_list, speakers_so_far, **kwargs):
-    """Returns the next speaker in the list of agents, in order. If no speakers have spoken yet, returns the first agent in the list."""
-    if len(speakers_so_far) == 0:
-        return agent_list[0]
-    most_recent_speaker = speakers_so_far[-1]
-    index = agent_list.index(most_recent_speaker)
-    return agent_list[(index + 1) % len(agent_list)]
-
-
-def turn_taking_generator_with_focal_speaker(
-    agent_list, speakers_so_far, focal_speaker_index, **kwargs
-):
-    """Returns the focal speaker first, then the next speaker in the list of agents sequentially, going back to the focal speaker after the last agent has spoken. If no speakers have spoken yet, returns the focal speaker.
-    This would be appropriate for say, a an auction where the auctioneer always speaks first, and then the next person in line speaks, and then the auctioneer speaks again.
-    """
-    if len(speakers_so_far) == 0:
-        return agent_list[focal_speaker_index]
-
-    most_recent_speaker = speakers_so_far[-1]
-    if most_recent_speaker == agent_list[focal_speaker_index]:
-        non_focal_agents = [
-            a for a in agent_list if a != agent_list[focal_speaker_index]
-        ]
-        non_focal_speakers = [
-            a for a in speakers_so_far if a != agent_list[focal_speaker_index]
-        ]
-        return default_turn_taking_generator(
-            agent_list=non_focal_agents, speakers_so_far=non_focal_speakers
-        )
-    else:
-        return agent_list[focal_speaker_index]
-
-
-def random_turn_taking_generator(agent_list, speakers_so_far, **kwargs):
-    """Returns a random speaker from the list of agents, but ensuring no agent speaks twice in a row.
-    If no speakers have spoken yet, returns a random agent."""
-    if len(speakers_so_far) == 0:
-        return random.choice(agent_list)
-    else:
-        most_recent_speaker = speakers_so_far[-1]
-    return random.choice([a for a in agent_list if a != most_recent_speaker])
-
-
-def random_inclusive_generator(agent_list, speakers_so_far, **kwargs):
-    """Returns a random speaker from the list of agents, but ensuring no agent speaks twice in a row and that
-    every agent has spoken before the same agent speaks again.
-    """
-    if len(speakers_so_far) > 0:
-        most_recent_speaker = speakers_so_far[-1]
-    else:
-        most_recent_speaker = None
-
-    lookback_length = len(speakers_so_far) % len(agent_list)
-
-    if lookback_length == 0:
-        eligible_agents = agent_list[:]
-    else:
-        eligible_agents = [
-            a for a in agent_list if a not in speakers_so_far[-lookback_length:]
-        ]
-
-    # don't have the same speaker twice in a row
-    if most_recent_speaker in eligible_agents:
-        eligible_agents.pop(eligible_agents.index(most_recent_speaker))
-
-    return random.choice(eligible_agents)
-
-
-def speaker_closure(agent_list, generator_function, focal_speaker_index=None):
-    speakers_so_far = []
-    focal_speaker_index = focal_speaker_index
-
-    def next_speaker_generator():
-        speaker = generator_function(
-            agent_list=agent_list,
-            speakers_so_far=speakers_so_far,
-            focal_speaker_index=focal_speaker_index,
-        )
-        speakers_so_far.append(speaker)
-        return speaker
-
-    return next_speaker_generator
-
-
-# speaker_gen = speaker_closure(agent_list = ['Alice', 'Bob', 'Charlie', "Mr.X"],
-#                               generator_function = turn_taking_generator_with_focal_speaker,
-#                               focal_speaker_index = 3)
-
-# for _ in range(30):
-#     print(speaker_gen())
+import random
+
+
+def default_turn_taking_generator(agent_list, speakers_so_far, **kwargs):
+    """Returns the next speaker in the list of agents, in order. If no speakers have spoken yet, returns the first agent in the list."""
+    if len(speakers_so_far) == 0:
+        return agent_list[0]
+    most_recent_speaker = speakers_so_far[-1]
+    index = agent_list.index(most_recent_speaker)
+    return agent_list[(index + 1) % len(agent_list)]
+
+
+def turn_taking_generator_with_focal_speaker(
+    agent_list, speakers_so_far, focal_speaker_index, **kwargs
+):
+    """Returns the focal speaker first, then the next speaker in the list of agents sequentially, going back to the focal speaker after the last agent has spoken. If no speakers have spoken yet, returns the focal speaker.
+    This would be appropriate for say, a an auction where the auctioneer always speaks first, and then the next person in line speaks, and then the auctioneer speaks again.
+    """
+    if len(speakers_so_far) == 0:
+        return agent_list[focal_speaker_index]
+
+    most_recent_speaker = speakers_so_far[-1]
+    if most_recent_speaker == agent_list[focal_speaker_index]:
+        non_focal_agents = [
+            a for a in agent_list if a != agent_list[focal_speaker_index]
+        ]
+        non_focal_speakers = [
+            a for a in speakers_so_far if a != agent_list[focal_speaker_index]
+        ]
+        return default_turn_taking_generator(
+            agent_list=non_focal_agents, speakers_so_far=non_focal_speakers
+        )
+    else:
+        return agent_list[focal_speaker_index]
+
+
+def random_turn_taking_generator(agent_list, speakers_so_far, **kwargs):
+    """Returns a random speaker from the list of agents, but ensuring no agent speaks twice in a row.
+    If no speakers have spoken yet, returns a random agent."""
+    if len(speakers_so_far) == 0:
+        return random.choice(agent_list)
+    else:
+        most_recent_speaker = speakers_so_far[-1]
+    return random.choice([a for a in agent_list if a != most_recent_speaker])
+
+
+def random_inclusive_generator(agent_list, speakers_so_far, **kwargs):
+    """Returns a random speaker from the list of agents, but ensuring no agent speaks twice in a row and that
+    every agent has spoken before the same agent speaks again.
+    """
+    if len(speakers_so_far) > 0:
+        most_recent_speaker = speakers_so_far[-1]
+    else:
+        most_recent_speaker = None
+
+    lookback_length = len(speakers_so_far) % len(agent_list)
+
+    if lookback_length == 0:
+        eligible_agents = agent_list[:]
+    else:
+        eligible_agents = [
+            a for a in agent_list if a not in speakers_so_far[-lookback_length:]
+        ]
+
+    # don't have the same speaker twice in a row
+    if most_recent_speaker in eligible_agents:
+        eligible_agents.pop(eligible_agents.index(most_recent_speaker))
+
+    return random.choice(eligible_agents)
+
+
+def speaker_closure(agent_list, generator_function, focal_speaker_index=None):
+    speakers_so_far = []
+    focal_speaker_index = focal_speaker_index
+
+    def next_speaker_generator():
+        speaker = generator_function(
+            agent_list=agent_list,
+            speakers_so_far=speakers_so_far,
+            focal_speaker_index=focal_speaker_index,
+        )
+        speakers_so_far.append(speaker)
+        return speaker
+
+    return next_speaker_generator
+
+
+# speaker_gen = speaker_closure(agent_list = ['Alice', 'Bob', 'Charlie', "Mr.X"],
+#                               generator_function = turn_taking_generator_with_focal_speaker,
+#                               focal_speaker_index = 3)
+
+# for _ in range(30):
+#     print(speaker_gen())